In [1]:
%run DEVDAN_sea.ipynb
Number of input:  3
Number of output:  2
Number of batch:  100
All Data
100% (100 of 100) |######################| Elapsed Time: 0:05:20 ETA:  00:00:00

=== Performance result ===
Accuracy:  91.92525252525252 (+/-) 6.080708747804398
Precision:  0.9192776971749151
Recall:  0.9192525252525252
F1 score:  0.9186067780776412
Testing Time:  0.0016018477353182707 (+/-) 0.0005982922835932849
Training Time:  3.236801999987978 (+/-) 0.33800646742671797


=== Average network evolution ===
Total hidden node:  24.19 (+/-) 10.065480614456519


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=3, out_features=41, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 3
No. of nodes : 41
No. of parameters : 167

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=41, out_features=2, bias=True)
)
No. of inputs : 41
No. of output : 2
No. of parameters : 84
100% (100 of 100) |######################| Elapsed Time: 0:04:56 ETA:  00:00:00

=== Performance result ===
Accuracy:  92.34646464646464 (+/-) 5.834611342795457
Precision:  0.9233072665145964
Recall:  0.9234646464646464
F1 score:  0.9230197967532785
Testing Time:  0.0015243930046004478 (+/-) 0.0005180127207044876
Training Time:  2.994499876041605 (+/-) 0.13171972905478677


=== Average network evolution ===
Total hidden node:  24.19 (+/-) 11.160371857604027


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=3, out_features=42, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 3
No. of nodes : 42
No. of parameters : 171

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=42, out_features=2, bias=True)
)
No. of inputs : 42
No. of output : 2
No. of parameters : 86
100% (100 of 100) |######################| Elapsed Time: 0:04:53 ETA:  00:00:00

=== Performance result ===
Accuracy:  92.54949494949494 (+/-) 5.947283120265988
Precision:  0.9252909406254234
Recall:  0.9254949494949495
F1 score:  0.925138674442084
Testing Time:  0.0015414724446306326 (+/-) 0.0004987503919768464
Training Time:  2.9658606269142846 (+/-) 0.06883233059119875


=== Average network evolution ===
Total hidden node:  21.85 (+/-) 10.446410866895864


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=3, out_features=38, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 3
No. of nodes : 38
No. of parameters : 155

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=38, out_features=2, bias=True)
)
No. of inputs : 38
No. of output : 2
No. of parameters : 78
100% (100 of 100) |######################| Elapsed Time: 0:05:38 ETA:  00:00:00

=== Performance result ===
Accuracy:  91.91111111111111 (+/-) 6.408404974795807
Precision:  0.9189998641859611
Recall:  0.9191111111111111
F1 score:  0.9185510936527751
Testing Time:  0.0016755238927976049 (+/-) 0.0007037523509520552
Training Time:  3.416408004182758 (+/-) 0.3602184100997241


=== Average network evolution ===
Total hidden node:  20.18 (+/-) 9.477742347204844


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=3, out_features=36, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 3
No. of nodes : 36
No. of parameters : 147

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=36, out_features=2, bias=True)
)
No. of inputs : 36
No. of output : 2
No. of parameters : 74
100% (100 of 100) |######################| Elapsed Time: 0:06:13 ETA:  00:00:00

=== Performance result ===
Accuracy:  91.9070707070707 (+/-) 6.1077075420523315
Precision:  0.9189647880251671
Recall:  0.919070707070707
F1 score:  0.9185060043371699
Testing Time:  0.0018411573737558693 (+/-) 0.0006024907397946985
Training Time:  3.7688460614946155 (+/-) 0.07927796664419721


=== Average network evolution ===
Total hidden node:  23.77 (+/-) 10.982581663707307


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=3, out_features=40, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 3
No. of nodes : 40
No. of parameters : 163

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=40, out_features=2, bias=True)
)
No. of inputs : 40
No. of output : 2
No. of parameters : 82

========== Performance occupancy ==========
Preq Accuracy:  92.13 (+/-) 0.27
F1 score:  0.92 (+/-) 0.0
Precision:  0.92 (+/-) 0.0
Recall:  0.92 (+/-) 0.0
Training time:  3.28 (+/-) 0.3
Testing time:  0.0 (+/-) 0.0


========== Network ==========
Number of hidden layers:  1.0 (+/-) 0.0
Number of features:  39.4 (+/-) 2.15
50% Data
100% (100 of 100) |######################| Elapsed Time: 0:04:43 ETA:  00:00:00

=== Performance result ===
Accuracy:  91.39999999999996 (+/-) 6.293543268198517
Precision:  0.9140736880099033
Recall:  0.914
F1 score:  0.913226848749671
Testing Time:  0.0016753215982456399 (+/-) 0.0006445702898571082
Training Time:  2.860139251959444 (+/-) 0.04804606533367886


=== Average network evolution ===
Total hidden node:  17.58 (+/-) 10.063975357680484


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=3, out_features=35, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 3
No. of nodes : 35
No. of parameters : 143

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=35, out_features=2, bias=True)
)
No. of inputs : 35
No. of output : 2
No. of parameters : 72
100% (100 of 100) |######################| Elapsed Time: 0:04:49 ETA:  00:00:00

=== Performance result ===
Accuracy:  91.72424242424243 (+/-) 6.5125223729674975
Precision:  0.9170373414728702
Recall:  0.9172424242424242
F1 score:  0.9167278007318695
Testing Time:  0.0017863788990059284 (+/-) 0.0005833241113596126
Training Time:  2.916241585606276 (+/-) 0.06202416120809332


=== Average network evolution ===
Total hidden node:  23.0 (+/-) 10.0687635785135


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=3, out_features=38, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 3
No. of nodes : 38
No. of parameters : 155

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=38, out_features=2, bias=True)
)
No. of inputs : 38
No. of output : 2
No. of parameters : 78
100% (100 of 100) |######################| Elapsed Time: 0:04:49 ETA:  00:00:00

=== Performance result ===
Accuracy:  91.56464646464649 (+/-) 6.469076607039062
Precision:  0.9155145236230928
Recall:  0.9156464646464646
F1 score:  0.9150368448204095
Testing Time:  0.0018366515034376973 (+/-) 0.0006241159766270944
Training Time:  2.9216011533833512 (+/-) 0.044804060749780855


=== Average network evolution ===
Total hidden node:  19.83 (+/-) 8.503005351050888


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=3, out_features=34, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 3
No. of nodes : 34
No. of parameters : 139

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=34, out_features=2, bias=True)
)
No. of inputs : 34
No. of output : 2
No. of parameters : 70
100% (100 of 100) |######################| Elapsed Time: 0:04:46 ETA:  00:00:00

=== Performance result ===
Accuracy:  91.53535353535354 (+/-) 6.771782110775629
Precision:  0.915421042988246
Recall:  0.9153535353535354
F1 score:  0.9146105883630826
Testing Time:  0.0018059123646129262 (+/-) 0.0006539972605315815
Training Time:  2.8862785401970448 (+/-) 0.10908190014071514


=== Average network evolution ===
Total hidden node:  20.35 (+/-) 8.54210161494231


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=3, out_features=34, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 3
No. of nodes : 34
No. of parameters : 139

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=34, out_features=2, bias=True)
)
No. of inputs : 34
No. of output : 2
No. of parameters : 70
100% (100 of 100) |######################| Elapsed Time: 0:04:46 ETA:  00:00:00

=== Performance result ===
Accuracy:  90.92121212121211 (+/-) 7.283872772856909
Precision:  0.9089107968957689
Recall:  0.9092121212121212
F1 score:  0.9089962523471589
Testing Time:  0.0018373980666651871 (+/-) 0.0006019725634470285
Training Time:  2.8923514539545234 (+/-) 0.052094178243336405


=== Average network evolution ===
Total hidden node:  18.0 (+/-) 9.691233151668573


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=3, out_features=34, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 3
No. of nodes : 34
No. of parameters : 139

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=34, out_features=2, bias=True)
)
No. of inputs : 34
No. of output : 2
No. of parameters : 70

========== Performance occupancy ==========
Preq Accuracy:  91.43 (+/-) 0.27
F1 score:  0.91 (+/-) 0.0
Precision:  0.91 (+/-) 0.0
Recall:  0.91 (+/-) 0.0
Training time:  2.9 (+/-) 0.02
Testing time:  0.0 (+/-) 0.0


========== Network ==========
Number of hidden layers:  1.0 (+/-) 0.0
Number of features:  35.0 (+/-) 1.55
25% Data
100% (100 of 100) |######################| Elapsed Time: 0:03:59 ETA:  00:00:00

=== Performance result ===
Accuracy:  91.37878787878788 (+/-) 6.1496041217296655
Precision:  0.9134581726611755
Recall:  0.9137878787878788
F1 score:  0.9134014220236669
Testing Time:  0.0017660555213388771 (+/-) 0.0007001542830051438
Training Time:  2.4162122986533423 (+/-) 0.040948938053211925


=== Average network evolution ===
Total hidden node:  17.08 (+/-) 5.790820321854236


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=3, out_features=27, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 3
No. of nodes : 27
No. of parameters : 111

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=27, out_features=2, bias=True)
)
No. of inputs : 27
No. of output : 2
No. of parameters : 56
100% (100 of 100) |######################| Elapsed Time: 0:03:58 ETA:  00:00:00

=== Performance result ===
Accuracy:  91.34747474747476 (+/-) 6.190712226030534
Precision:  0.9134210808651505
Recall:  0.9134747474747474
F1 score:  0.9127670902922834
Testing Time:  0.0017683192937061041 (+/-) 0.0006461541402412309
Training Time:  2.40095814309939 (+/-) 0.040973986613750096


=== Average network evolution ===
Total hidden node:  19.75 (+/-) 6.630799348494871


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=3, out_features=31, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 3
No. of nodes : 31
No. of parameters : 127

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=31, out_features=2, bias=True)
)
No. of inputs : 31
No. of output : 2
No. of parameters : 64
100% (100 of 100) |######################| Elapsed Time: 0:03:59 ETA:  00:00:00

=== Performance result ===
Accuracy:  90.64141414141412 (+/-) 7.349885041374196
Precision:  0.9063068097474899
Recall:  0.9064141414141414
F1 score:  0.9055924012407242
Testing Time:  0.0017155998885029493 (+/-) 0.0006470350971316688
Training Time:  2.4141599987492417 (+/-) 0.04049285263299466


=== Average network evolution ===
Total hidden node:  14.86 (+/-) 6.648338138211683


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=3, out_features=27, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 3
No. of nodes : 27
No. of parameters : 111

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=27, out_features=2, bias=True)
)
No. of inputs : 27
No. of output : 2
No. of parameters : 56
100% (100 of 100) |######################| Elapsed Time: 0:04:00 ETA:  00:00:00

=== Performance result ===
Accuracy:  91.05454545454545 (+/-) 6.945142517714682
Precision:  0.9103031200487123
Recall:  0.9105454545454545
F1 score:  0.9099273509970811
Testing Time:  0.0019661970812864978 (+/-) 0.0012452893604838657
Training Time:  2.4292060871316927 (+/-) 0.04447180485965453


=== Average network evolution ===
Total hidden node:  16.86 (+/-) 6.519233083730017


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=3, out_features=28, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 3
No. of nodes : 28
No. of parameters : 115

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=28, out_features=2, bias=True)
)
No. of inputs : 28
No. of output : 2
No. of parameters : 58
100% (100 of 100) |######################| Elapsed Time: 0:04:01 ETA:  00:00:00

=== Performance result ===
Accuracy:  90.7727272727273 (+/-) 7.237204915312672
Precision:  0.90740060769996
Recall:  0.9077272727272727
F1 score:  0.9071429720777046
Testing Time:  0.001739099772289546 (+/-) 0.0005713936475549902
Training Time:  2.430939387793493 (+/-) 0.08472854132452794


=== Average network evolution ===
Total hidden node:  15.28 (+/-) 7.686455620115165


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=3, out_features=28, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 3
No. of nodes : 28
No. of parameters : 115

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=28, out_features=2, bias=True)
)
No. of inputs : 28
No. of output : 2
No. of parameters : 58
N/A% (0 of 100) |                        | Elapsed Time: 0:00:00 ETA:  --:--:--

========== Performance occupancy ==========
Preq Accuracy:  91.04 (+/-) 0.3
F1 score:  0.91 (+/-) 0.0
Precision:  0.91 (+/-) 0.0
Recall:  0.91 (+/-) 0.0
Training time:  2.42 (+/-) 0.01
Testing time:  0.0 (+/-) 0.0


========== Network ==========
Number of hidden layers:  1.0 (+/-) 0.0
Number of features:  28.2 (+/-) 1.47
Infinite Delay
100% (100 of 100) |######################| Elapsed Time: 0:03:19 ETA:  00:00:00

=== Performance result ===
Accuracy:  74.6050505050505 (+/-) 7.964103476811964
Precision:  0.7880601214303441
Recall:  0.7460505050505051
F1 score:  0.7092281958038471
Testing Time:  0.0016816842435586332 (+/-) 0.0006595471978042406
Training Time:  1.9759978381070225 (+/-) 0.04661539567161622


=== Average network evolution ===
Total hidden node:  11.06 (+/-) 11.06


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=3, out_features=10, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 3
No. of nodes : 10
No. of parameters : 43

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=10, out_features=2, bias=True)
)
No. of inputs : 10
No. of output : 2
No. of parameters : 22
100% (100 of 100) |######################| Elapsed Time: 0:03:19 ETA:  00:00:00

=== Performance result ===
Accuracy:  75.94848484848484 (+/-) 7.867146411108086
Precision:  0.8083488730562184
Recall:  0.7594848484848484
F1 score:  0.7251637414309624
Testing Time:  0.0017073852847320865 (+/-) 0.0006031628478924322
Training Time:  1.9699685308668349 (+/-) 0.03765807210050614


=== Average network evolution ===
Total hidden node:  12.24 (+/-) 12.24


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=3, out_features=13, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 3
No. of nodes : 13
No. of parameters : 55

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=13, out_features=2, bias=True)
)
No. of inputs : 13
No. of output : 2
No. of parameters : 28
100% (100 of 100) |######################| Elapsed Time: 0:02:59 ETA:  00:00:00

=== Performance result ===
Accuracy:  57.881818181818176 (+/-) 9.066759843954854
Precision:  0.769403021109308
Recall:  0.5788181818181818
F1 score:  0.5557339157018713
Testing Time:  0.0015139724269057765 (+/-) 0.0005191192721505033
Training Time:  1.7734314432047835 (+/-) 0.23507604624415554


=== Average network evolution ===
Total hidden node:  9.98 (+/-) 9.98


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=3, out_features=10, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 3
No. of nodes : 10
No. of parameters : 43

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=10, out_features=2, bias=True)
)
No. of inputs : 10
No. of output : 2
No. of parameters : 22
100% (100 of 100) |######################| Elapsed Time: 0:03:04 ETA:  00:00:00

=== Performance result ===
Accuracy:  80.28686868686869 (+/-) 6.326561714246609
Precision:  0.8111327238727221
Recall:  0.8028686868686868
F1 score:  0.7916855797773654
Testing Time:  0.0014902678402987394 (+/-) 0.0005939682096889087
Training Time:  1.8313889961050014 (+/-) 0.24555669559995505


=== Average network evolution ===
Total hidden node:  2.52 (+/-) 2.52


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=3, out_features=2, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 3
No. of nodes : 2
No. of parameters : 11

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=2, out_features=2, bias=True)
)
No. of inputs : 2
No. of output : 2
No. of parameters : 6
100% (100 of 100) |######################| Elapsed Time: 0:03:04 ETA:  00:00:00

=== Performance result ===
Accuracy:  83.60808080808081 (+/-) 5.931437844448929
Precision:  0.8355603943910512
Recall:  0.8360808080808081
F1 score:  0.8327194163280498
Testing Time:  0.0014853236651179767 (+/-) 0.0006089309475658081
Training Time:  1.8211949305100874 (+/-) 0.23378756533230002


=== Average network evolution ===
Total hidden node:  7.96 (+/-) 7.96


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=3, out_features=8, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 3
No. of nodes : 8
No. of parameters : 35

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=8, out_features=2, bias=True)
)
No. of inputs : 8
No. of output : 2
No. of parameters : 18

========== Performance occupancy ==========
Preq Accuracy:  74.47 (+/-) 8.88
F1 score:  0.72 (+/-) 0.09
Precision:  0.8 (+/-) 0.02
Recall:  0.74 (+/-) 0.09
Training time:  1.87 (+/-) 0.08
Testing time:  0.0 (+/-) 0.0


========== Network ==========
Number of hidden layers:  1.0 (+/-) 0.0
Number of features:  8.6 (+/-) 3.67
In [2]:
%run DEVDAN_hyperplane.ipynb
Number of input:  4
Number of output:  2
Number of batch:  120
All Data
100% (120 of 120) |######################| Elapsed Time: 0:06:46 ETA:  00:00:00

=== Performance result ===
Accuracy:  91.85630252100842 (+/-) 2.4846296802495216
Precision:  0.9185662008403982
Recall:  0.918563025210084
F1 score:  0.9185630546253908
Testing Time:  0.0016164499170639936 (+/-) 0.0006308179755702654
Training Time:  3.409361683020071 (+/-) 0.11576049211825501


=== Average network evolution ===
Total hidden node:  8.658333333333333 (+/-) 0.8514285381378496


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=4, out_features=9, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 4
No. of nodes : 9
No. of parameters : 49

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=9, out_features=2, bias=True)
)
No. of inputs : 9
No. of output : 2
No. of parameters : 20
100% (120 of 120) |######################| Elapsed Time: 0:06:37 ETA:  00:00:00

=== Performance result ===
Accuracy:  91.7361344537815 (+/-) 1.9788686646683282
Precision:  0.9174344184343703
Recall:  0.9173613445378151
F1 score:  0.9173586657913918
Testing Time:  0.00160390990121024 (+/-) 0.0005827877406234725
Training Time:  3.3403382882350634 (+/-) 0.0797951751431891


=== Average network evolution ===
Total hidden node:  8.383333333333333 (+/-) 0.6853628398317363


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=4, out_features=9, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 4
No. of nodes : 9
No. of parameters : 49

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=9, out_features=2, bias=True)
)
No. of inputs : 9
No. of output : 2
No. of parameters : 20
100% (120 of 120) |######################| Elapsed Time: 0:06:27 ETA:  00:00:00

=== Performance result ===
Accuracy:  91.30168067226889 (+/-) 3.0117133567801484
Precision:  0.9132557785397316
Recall:  0.913016806722689
F1 score:  0.9130060434286155
Testing Time:  0.0015609304444128725 (+/-) 0.0005599276659532174
Training Time:  3.2499673887461173 (+/-) 0.18157636649205716


=== Average network evolution ===
Total hidden node:  12.625 (+/-) 1.5867288153094508


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=4, out_features=13, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 4
No. of nodes : 13
No. of parameters : 69

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=13, out_features=2, bias=True)
)
No. of inputs : 13
No. of output : 2
No. of parameters : 28
100% (120 of 120) |######################| Elapsed Time: 0:06:54 ETA:  00:00:00

=== Performance result ===
Accuracy:  91.3747899159664 (+/-) 3.698494322015696
Precision:  0.9139490818146658
Recall:  0.9137478991596638
F1 score:  0.9137390640896543
Testing Time:  0.0016546389635871438 (+/-) 0.0005697500949408061
Training Time:  3.4754735241417123 (+/-) 0.3521201829537271


=== Average network evolution ===
Total hidden node:  10.916666666666666 (+/-) 1.2354711202164494


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=4, out_features=12, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 4
No. of nodes : 12
No. of parameters : 64

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=12, out_features=2, bias=True)
)
No. of inputs : 12
No. of output : 2
No. of parameters : 26
100% (120 of 120) |######################| Elapsed Time: 0:07:27 ETA:  00:00:00

=== Performance result ===
Accuracy:  92.27983193277309 (+/-) 2.1203923781459957
Precision:  0.9227995428796716
Recall:  0.922798319327731
F1 score:  0.9227983674936292
Testing Time:  0.0017458350718522271 (+/-) 0.0006467998789099099
Training Time:  3.757355964484335 (+/-) 0.21553145588596484


=== Average network evolution ===
Total hidden node:  9.891666666666667 (+/-) 1.1090223422255998


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=4, out_features=11, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 4
No. of nodes : 11
No. of parameters : 59

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=11, out_features=2, bias=True)
)
No. of inputs : 11
No. of output : 2
No. of parameters : 24

========== Performance occupancy ==========
Preq Accuracy:  91.71 (+/-) 0.35
F1 score:  0.92 (+/-) 0.0
Precision:  0.92 (+/-) 0.0
Recall:  0.92 (+/-) 0.0
Training time:  3.45 (+/-) 0.17
Testing time:  0.0 (+/-) 0.0


========== Network ==========
Number of hidden layers:  1.0 (+/-) 0.0
Number of features:  10.8 (+/-) 1.6
50% Data
100% (120 of 120) |######################| Elapsed Time: 0:05:50 ETA:  00:00:00

=== Performance result ===
Accuracy:  91.58823529411761 (+/-) 3.243304064616984
Precision:  0.9158913889413053
Recall:  0.9158823529411765
F1 score:  0.9158822255855401
Testing Time:  0.0017175834719874278 (+/-) 0.000627979051912992
Training Time:  2.940670784781961 (+/-) 0.09285771106225826


=== Average network evolution ===
Total hidden node:  8.891666666666667 (+/-) 1.4537069473896342


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=4, out_features=10, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 4
No. of nodes : 10
No. of parameters : 54

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=10, out_features=2, bias=True)
)
No. of inputs : 10
No. of output : 2
No. of parameters : 22
100% (120 of 120) |######################| Elapsed Time: 0:05:48 ETA:  00:00:00

=== Performance result ===
Accuracy:  90.96554621848739 (+/-) 3.4593300214700076
Precision:  0.9098527037902825
Recall:  0.9096554621848739
F1 score:  0.9096463155161267
Testing Time:  0.0016743515719886588 (+/-) 0.0006054548508114766
Training Time:  2.9264531616403273 (+/-) 0.07038351093645351


=== Average network evolution ===
Total hidden node:  7.366666666666666 (+/-) 1.2905640455070628


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=4, out_features=9, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 4
No. of nodes : 9
No. of parameters : 49

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=9, out_features=2, bias=True)
)
No. of inputs : 9
No. of output : 2
No. of parameters : 20
100% (120 of 120) |######################| Elapsed Time: 0:05:22 ETA:  00:00:00

=== Performance result ===
Accuracy:  90.85714285714286 (+/-) 3.3291322065216025
Precision:  0.908832793807178
Recall:  0.9085714285714286
F1 score:  0.9085588296288148
Testing Time:  0.0017051416284897748 (+/-) 0.0005645431991933695
Training Time:  2.7088816907225537 (+/-) 0.33067538475833785


=== Average network evolution ===
Total hidden node:  10.875 (+/-) 0.9709316831442536


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=4, out_features=12, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 4
No. of nodes : 12
No. of parameters : 64

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=12, out_features=2, bias=True)
)
No. of inputs : 12
No. of output : 2
No. of parameters : 26
100% (120 of 120) |######################| Elapsed Time: 0:04:11 ETA:  00:00:00

=== Performance result ===
Accuracy:  90.79495798319329 (+/-) 4.084235911578549
Precision:  0.9080071069722248
Recall:  0.9079495798319328
F1 score:  0.9079472815001712
Testing Time:  0.0014418894503296924 (+/-) 0.0004986817481041347
Training Time:  2.106316370122573 (+/-) 0.05737595003662739


=== Average network evolution ===
Total hidden node:  11.058333333333334 (+/-) 0.8971792215357844


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=4, out_features=12, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 4
No. of nodes : 12
No. of parameters : 64

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=12, out_features=2, bias=True)
)
No. of inputs : 12
No. of output : 2
No. of parameters : 26
100% (120 of 120) |######################| Elapsed Time: 0:04:17 ETA:  00:00:00

=== Performance result ===
Accuracy:  91.22689075630255 (+/-) 3.4619345997490725
Precision:  0.9123051571718592
Recall:  0.9122689075630253
F1 score:  0.9122676853507298
Testing Time:  0.0014235272127039293 (+/-) 0.0005127906568978413
Training Time:  2.16469283464576 (+/-) 0.17187148708337796


=== Average network evolution ===
Total hidden node:  11.033333333333333 (+/-) 1.667999467092907


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=4, out_features=12, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 4
No. of nodes : 12
No. of parameters : 64

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=12, out_features=2, bias=True)
)
No. of inputs : 12
No. of output : 2
No. of parameters : 26

========== Performance occupancy ==========
Preq Accuracy:  91.09 (+/-) 0.29
F1 score:  0.91 (+/-) 0.0
Precision:  0.91 (+/-) 0.0
Recall:  0.91 (+/-) 0.0
Training time:  2.57 (+/-) 0.36
Testing time:  0.0 (+/-) 0.0


========== Network ==========
Number of hidden layers:  1.0 (+/-) 0.0
Number of features:  11.0 (+/-) 1.26
25% Data
100% (120 of 120) |######################| Elapsed Time: 0:03:59 ETA:  00:00:00

=== Performance result ===
Accuracy:  90.04033613445381 (+/-) 5.224687990004378
Precision:  0.9004311368867022
Recall:  0.9004033613445378
F1 score:  0.9004023537390634
Testing Time:  0.0015495184088955406 (+/-) 0.0005673006966479277
Training Time:  2.0059585691500113 (+/-) 0.13431909829980931


=== Average network evolution ===
Total hidden node:  12.558333333333334 (+/-) 1.7068286055983735


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=4, out_features=14, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 4
No. of nodes : 14
No. of parameters : 74

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=14, out_features=2, bias=True)
)
No. of inputs : 14
No. of output : 2
No. of parameters : 30
100% (120 of 120) |######################| Elapsed Time: 0:04:03 ETA:  00:00:00

=== Performance result ===
Accuracy:  89.9983193277311 (+/-) 6.110192382965803
Precision:  0.900059482624946
Recall:  0.8999831932773109
F1 score:  0.8999796347825514
Testing Time:  0.0016129237263142562 (+/-) 0.0005046553001506729
Training Time:  2.0459356287948225 (+/-) 0.04598585728298637


=== Average network evolution ===
Total hidden node:  12.025 (+/-) 2.6059627139824295


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=4, out_features=14, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 4
No. of nodes : 14
No. of parameters : 74

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=14, out_features=2, bias=True)
)
No. of inputs : 14
No. of output : 2
No. of parameters : 30
100% (120 of 120) |######################| Elapsed Time: 0:04:02 ETA:  00:00:00

=== Performance result ===
Accuracy:  90.21512605042017 (+/-) 3.546939470298307
Precision:  0.9021670871388804
Recall:  0.9021512605042017
F1 score:  0.9021508252729623
Testing Time:  0.0015794729986110655 (+/-) 0.0005107477592847049
Training Time:  2.035938004485699 (+/-) 0.027089092148911555


=== Average network evolution ===
Total hidden node:  10.741666666666667 (+/-) 1.2941910815469082


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=4, out_features=12, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 4
No. of nodes : 12
No. of parameters : 64

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=12, out_features=2, bias=True)
)
No. of inputs : 12
No. of output : 2
No. of parameters : 26
100% (120 of 120) |######################| Elapsed Time: 0:04:02 ETA:  00:00:00

=== Performance result ===
Accuracy:  90.79411764705883 (+/-) 3.042729151936058
Precision:  0.9081263879798764
Recall:  0.9079411764705883
F1 score:  0.9079324403317255
Testing Time:  0.0016272448692001215 (+/-) 0.0005138433361262728
Training Time:  2.0324966246340455 (+/-) 0.020026302197294177


=== Average network evolution ===
Total hidden node:  9.266666666666667 (+/-) 1.1883695646650592


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=4, out_features=10, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 4
No. of nodes : 10
No. of parameters : 54

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=10, out_features=2, bias=True)
)
No. of inputs : 10
No. of output : 2
No. of parameters : 22
100% (120 of 120) |######################| Elapsed Time: 0:04:01 ETA:  00:00:00

=== Performance result ===
Accuracy:  89.56302521008402 (+/-) 7.404789110600903
Precision:  0.8963435630290143
Recall:  0.8956302521008404
F1 score:  0.8955872091396918
Testing Time:  0.0015367339639102712 (+/-) 0.0005471801792978896
Training Time:  2.0300943631084025 (+/-) 0.019507861707926268


=== Average network evolution ===
Total hidden node:  9.25 (+/-) 1.8984642916490861


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=4, out_features=11, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 4
No. of nodes : 11
No. of parameters : 59

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=11, out_features=2, bias=True)
)
No. of inputs : 11
No. of output : 2
No. of parameters : 24
N/A% (0 of 120) |                        | Elapsed Time: 0:00:00 ETA:  --:--:--

========== Performance occupancy ==========
Preq Accuracy:  90.12 (+/-) 0.4
F1 score:  0.9 (+/-) 0.0
Precision:  0.9 (+/-) 0.0
Recall:  0.9 (+/-) 0.0
Training time:  2.03 (+/-) 0.01
Testing time:  0.0 (+/-) 0.0


========== Network ==========
Number of hidden layers:  1.0 (+/-) 0.0
Number of features:  12.2 (+/-) 1.6
Infinite Delay
100% (120 of 120) |######################| Elapsed Time: 0:03:22 ETA:  00:00:00

=== Performance result ===
Accuracy:  56.01092436974789 (+/-) 9.945750242442063
Precision:  0.7217668208630682
Recall:  0.5601092436974789
F1 score:  0.4614369828794625
Testing Time:  0.001488076538598838 (+/-) 0.0005172047536335391
Training Time:  1.6679233863574117 (+/-) 0.03211003987336133


=== Average network evolution ===
Total hidden node:  2.2416666666666667 (+/-) 2.2416666666666667


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=4, out_features=2, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 4
No. of nodes : 2
No. of parameters : 14

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=2, out_features=2, bias=True)
)
No. of inputs : 2
No. of output : 2
No. of parameters : 6
100% (120 of 120) |######################| Elapsed Time: 0:03:21 ETA:  00:00:00

=== Performance result ===
Accuracy:  77.69747899159665 (+/-) 9.217625263225672
Precision:  0.8087717543957658
Recall:  0.7769747899159664
F1 score:  0.7710047302207703
Testing Time:  0.0015065369485807018 (+/-) 0.0005019445951762001
Training Time:  1.6616621438194723 (+/-) 0.018153549181321938


=== Average network evolution ===
Total hidden node:  4.641666666666667 (+/-) 4.641666666666667


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=4, out_features=5, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 4
No. of nodes : 5
No. of parameters : 29

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=5, out_features=2, bias=True)
)
No. of inputs : 5
No. of output : 2
No. of parameters : 12
100% (120 of 120) |######################| Elapsed Time: 0:03:20 ETA:  00:00:00

=== Performance result ===
Accuracy:  86.4252100840336 (+/-) 3.2580403061559826
Precision:  0.8644107153168673
Recall:  0.8642521008403361
F1 score:  0.8642399442079186
Testing Time:  0.0015534312785172662 (+/-) 0.0005123165606415981
Training Time:  1.6594710850915988 (+/-) 0.01721401430479802


=== Average network evolution ===
Total hidden node:  6.983333333333333 (+/-) 6.983333333333333


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=4, out_features=7, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 4
No. of nodes : 7
No. of parameters : 39

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=7, out_features=2, bias=True)
)
No. of inputs : 7
No. of output : 2
No. of parameters : 16
100% (120 of 120) |######################| Elapsed Time: 0:03:21 ETA:  00:00:00

=== Performance result ===
Accuracy:  78.64789915966387 (+/-) 3.5135714966541003
Precision:  0.789667494038251
Recall:  0.7864789915966387
F1 score:  0.7859138592001494
Testing Time:  0.0015362350880598822 (+/-) 0.0005496850381586778
Training Time:  1.666143870153347 (+/-) 0.025121387579147808


=== Average network evolution ===
Total hidden node:  4.716666666666667 (+/-) 4.716666666666667


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=4, out_features=4, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 4
No. of nodes : 4
No. of parameters : 24

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=4, out_features=2, bias=True)
)
No. of inputs : 4
No. of output : 2
No. of parameters : 10
100% (120 of 120) |######################| Elapsed Time: 0:03:22 ETA:  00:00:00

=== Performance result ===
Accuracy:  76.63025210084034 (+/-) 5.227537856131268
Precision:  0.819552281461266
Recall:  0.7663025210084033
F1 score:  0.7562451892787713
Testing Time:  0.0014777604271383846 (+/-) 0.0005202872553361456
Training Time:  1.6731170085297913 (+/-) 0.023915686972821818


=== Average network evolution ===
Total hidden node:  8.958333333333334 (+/-) 8.958333333333334


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=4, out_features=9, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 4
No. of nodes : 9
No. of parameters : 49

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=9, out_features=2, bias=True)
)
No. of inputs : 9
No. of output : 2
No. of parameters : 20

========== Performance occupancy ==========
Preq Accuracy:  75.08 (+/-) 10.14
F1 score:  0.73 (+/-) 0.14
Precision:  0.8 (+/-) 0.05
Recall:  0.75 (+/-) 0.1
Training time:  1.67 (+/-) 0.0
Testing time:  0.0 (+/-) 0.0


========== Network ==========
Number of hidden layers:  1.0 (+/-) 0.0
Number of features:  5.4 (+/-) 2.42
In [3]:
%run DEVDAN_weather.ipynb
Number of input:  8
Number of output:  2
Number of batch:  18
All Data
100% (18 of 18) |########################| Elapsed Time: 0:00:55 ETA:  00:00:00

=== Performance result ===
Accuracy:  75.19411764705882 (+/-) 2.743649477748097
Precision:  0.7448029154092382
Recall:  0.7519411764705882
F1 score:  0.7471241306691262
Testing Time:  0.0018139165990492877 (+/-) 0.0006275018204258435
Training Time:  3.249160850749296 (+/-) 0.15658638474850642


=== Average network evolution ===
Total hidden node:  13.11111111111111 (+/-) 0.5665577237325317


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=15, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 15
No. of parameters : 143

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=15, out_features=2, bias=True)
)
No. of inputs : 15
No. of output : 2
No. of parameters : 32
100% (18 of 18) |########################| Elapsed Time: 0:00:52 ETA:  00:00:00

=== Performance result ===
Accuracy:  74.61764705882354 (+/-) 2.4353367430199704
Precision:  0.7401296279707679
Recall:  0.7461764705882353
F1 score:  0.742390592572663
Testing Time:  0.001689896864049575 (+/-) 0.000569321351826984
Training Time:  3.1122857682845173 (+/-) 0.04266007794062158


=== Average network evolution ===
Total hidden node:  8.555555555555555 (+/-) 1.2120791238484128


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=11, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 11
No. of parameters : 107

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=11, out_features=2, bias=True)
)
No. of inputs : 11
No. of output : 2
No. of parameters : 24
100% (18 of 18) |########################| Elapsed Time: 0:00:52 ETA:  00:00:00

=== Performance result ===
Accuracy:  74.05882352941177 (+/-) 2.94279955215306
Precision:  0.7335877144267555
Recall:  0.7405882352941177
F1 score:  0.7361008165090327
Testing Time:  0.001869664472692153 (+/-) 0.00032897344308848044
Training Time:  3.1055023389704086 (+/-) 0.01389836774700889


=== Average network evolution ===
Total hidden node:  13.38888888888889 (+/-) 1.0076865081787252


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=15, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 15
No. of parameters : 143

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=15, out_features=2, bias=True)
)
No. of inputs : 15
No. of output : 2
No. of parameters : 32
100% (18 of 18) |########################| Elapsed Time: 0:00:52 ETA:  00:00:00

=== Performance result ===
Accuracy:  73.85882352941177 (+/-) 3.077634466604928
Precision:  0.7277563598384913
Recall:  0.7385882352941177
F1 score:  0.7302970390142409
Testing Time:  0.001766807892743279 (+/-) 0.0006294903402457582
Training Time:  3.10989907208611 (+/-) 0.024054273087786827


=== Average network evolution ===
Total hidden node:  11.555555555555555 (+/-) 1.8324913891634047


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=15, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 15
No. of parameters : 143

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=15, out_features=2, bias=True)
)
No. of inputs : 15
No. of output : 2
No. of parameters : 32
100% (18 of 18) |########################| Elapsed Time: 0:00:53 ETA:  00:00:00

=== Performance result ===
Accuracy:  73.1705882352941 (+/-) 4.845223810271955
Precision:  0.7204882096882087
Recall:  0.7317058823529412
F1 score:  0.7233670010440546
Testing Time:  0.001747439889346852 (+/-) 0.00042623322455200566
Training Time:  3.1214717275956096 (+/-) 0.04983836196406317


=== Average network evolution ===
Total hidden node:  12.277777777777779 (+/-) 1.2385276005337753


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=14, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 14
No. of parameters : 134

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=14, out_features=2, bias=True)
)
No. of inputs : 14
No. of output : 2
No. of parameters : 30

========== Performance occupancy ==========
Preq Accuracy:  74.18 (+/-) 0.69
F1 score:  0.74 (+/-) 0.01
Precision:  0.73 (+/-) 0.01
Recall:  0.74 (+/-) 0.01
Training time:  3.14 (+/-) 0.05
Testing time:  0.0 (+/-) 0.0


========== Network ==========
Number of hidden layers:  1.0 (+/-) 0.0
Number of features:  14.0 (+/-) 1.55
50% Data
100% (18 of 18) |########################| Elapsed Time: 0:00:40 ETA:  00:00:00

=== Performance result ===
Accuracy:  73.84117647058824 (+/-) 3.543188797003495
Precision:  0.7230565009461757
Recall:  0.7384117647058823
F1 score:  0.7187420830536322
Testing Time:  0.0015752035028794233 (+/-) 0.0004918285294427089
Training Time:  2.3648371275733497 (+/-) 0.01885704170853602


=== Average network evolution ===
Total hidden node:  8.166666666666666 (+/-) 0.7637626158259734


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=10, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 10
No. of parameters : 98

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=10, out_features=2, bias=True)
)
No. of inputs : 10
No. of output : 2
No. of parameters : 22
100% (18 of 18) |########################| Elapsed Time: 0:00:40 ETA:  00:00:00

=== Performance result ===
Accuracy:  71.00588235294117 (+/-) 4.4800827970599055
Precision:  0.686885553081282
Recall:  0.7100588235294117
F1 score:  0.6843836439652206
Testing Time:  0.0013497717240277458 (+/-) 0.0004721289819953139
Training Time:  2.3712027072906494 (+/-) 0.01679469751286845


=== Average network evolution ===
Total hidden node:  4.5 (+/-) 0.6009252125773316


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=6, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 6
No. of parameters : 62

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=6, out_features=2, bias=True)
)
No. of inputs : 6
No. of output : 2
No. of parameters : 14
100% (18 of 18) |########################| Elapsed Time: 0:00:40 ETA:  00:00:00

=== Performance result ===
Accuracy:  70.86470588235294 (+/-) 2.93657286775119
Precision:  0.6860548442934544
Recall:  0.7086470588235294
F1 score:  0.6854351679566539
Testing Time:  0.0016374588012695312 (+/-) 0.00048341220600342267
Training Time:  2.3747700943666348 (+/-) 0.0330317355142675


=== Average network evolution ===
Total hidden node:  7.444444444444445 (+/-) 0.7617394000445604


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=9, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 9
No. of parameters : 89

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=9, out_features=2, bias=True)
)
No. of inputs : 9
No. of output : 2
No. of parameters : 20
100% (18 of 18) |########################| Elapsed Time: 0:00:40 ETA:  00:00:00

=== Performance result ===
Accuracy:  71.30588235294118 (+/-) 3.9717340394690086
Precision:  0.6942250575112038
Recall:  0.7130588235294117
F1 score:  0.6960409308094037
Testing Time:  0.0015714589287252987 (+/-) 0.000495141777230886
Training Time:  2.3792358005748078 (+/-) 0.017539975966491535


=== Average network evolution ===
Total hidden node:  11.555555555555555 (+/-) 1.7069212773041351


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=14, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 14
No. of parameters : 134

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=14, out_features=2, bias=True)
)
No. of inputs : 14
No. of output : 2
No. of parameters : 30
100% (18 of 18) |########################| Elapsed Time: 0:00:40 ETA:  00:00:00

=== Performance result ===
Accuracy:  71.98823529411764 (+/-) 2.761261935066726
Precision:  0.7002518380302651
Recall:  0.7198823529411764
F1 score:  0.6984202365610607
Testing Time:  0.0017408062429989084 (+/-) 0.0004277304053071516
Training Time:  2.3812663134406593 (+/-) 0.020216228023296538


=== Average network evolution ===
Total hidden node:  10.722222222222221 (+/-) 0.9891385452647142


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=12, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 12
No. of parameters : 116

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=12, out_features=2, bias=True)
)
No. of inputs : 12
No. of output : 2
No. of parameters : 26

========== Performance occupancy ==========
Preq Accuracy:  71.8 (+/-) 1.09
F1 score:  0.7 (+/-) 0.01
Precision:  0.7 (+/-) 0.01
Recall:  0.72 (+/-) 0.01
Training time:  2.37 (+/-) 0.01
Testing time:  0.0 (+/-) 0.0


========== Network ==========
Number of hidden layers:  1.0 (+/-) 0.0
Number of features:  10.2 (+/-) 2.71
25% Data
100% (18 of 18) |########################| Elapsed Time: 0:00:34 ETA:  00:00:00

=== Performance result ===
Accuracy:  70.4764705882353 (+/-) 2.9538667403461485
Precision:  0.6767315653230589
Recall:  0.704764705882353
F1 score:  0.6596906561897511
Testing Time:  0.0018053756040685316 (+/-) 0.0005124279597660776
Training Time:  2.007312900879804 (+/-) 0.009553546748353826


=== Average network evolution ===
Total hidden node:  9.222222222222221 (+/-) 0.9749960430435692


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=11, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 11
No. of parameters : 107

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=11, out_features=2, bias=True)
)
No. of inputs : 11
No. of output : 2
No. of parameters : 24
100% (18 of 18) |########################| Elapsed Time: 0:00:34 ETA:  00:00:00

=== Performance result ===
Accuracy:  69.2764705882353 (+/-) 5.193381468047996
Precision:  0.6716694552604342
Recall:  0.692764705882353
F1 score:  0.6759251589337258
Testing Time:  0.0016939780291389016 (+/-) 0.00045877167359273206
Training Time:  2.017654446994557 (+/-) 0.02622129294336216


=== Average network evolution ===
Total hidden node:  6.277777777777778 (+/-) 0.8695819912499182


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=8, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 8
No. of parameters : 80

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=8, out_features=2, bias=True)
)
No. of inputs : 8
No. of output : 2
No. of parameters : 18
100% (18 of 18) |########################| Elapsed Time: 0:00:34 ETA:  00:00:00

=== Performance result ===
Accuracy:  71.68823529411766 (+/-) 3.7504325010106068
Precision:  0.6990627425274522
Recall:  0.7168823529411765
F1 score:  0.7007922792104412
Testing Time:  0.001744536792530733 (+/-) 0.0005503991362091711
Training Time:  2.0143559399773094 (+/-) 0.01785212149113314


=== Average network evolution ===
Total hidden node:  12.666666666666666 (+/-) 0.7453559924999299


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=14, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 14
No. of parameters : 134

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=14, out_features=2, bias=True)
)
No. of inputs : 14
No. of output : 2
No. of parameters : 30
100% (18 of 18) |########################| Elapsed Time: 0:00:34 ETA:  00:00:00

=== Performance result ===
Accuracy:  72.34117647058824 (+/-) 2.5566657568770204
Precision:  0.7048955411046023
Recall:  0.7234117647058823
F1 score:  0.6871293813727632
Testing Time:  0.001753414378446691 (+/-) 0.0005463205231052841
Training Time:  2.0055096990921917 (+/-) 0.015670665188447896


=== Average network evolution ===
Total hidden node:  11.944444444444445 (+/-) 1.0786937688304221


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=14, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 14
No. of parameters : 134

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=14, out_features=2, bias=True)
)
No. of inputs : 14
No. of output : 2
No. of parameters : 30
100% (18 of 18) |########################| Elapsed Time: 0:00:34 ETA:  00:00:00

=== Performance result ===
Accuracy:  68.88823529411765 (+/-) 3.8527121620308216
Precision:  0.6489131204840051
Recall:  0.6888823529411765
F1 score:  0.5848684981101093
Testing Time:  0.0016893639284021715 (+/-) 0.0005722985048259948
Training Time:  2.0114390289082245 (+/-) 0.013226225262863047


=== Average network evolution ===
Total hidden node:  5.888888888888889 (+/-) 0.5665577237325317


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=7, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 7
No. of parameters : 71

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=7, out_features=2, bias=True)
)
No. of inputs : 7
No. of output : 2
No. of parameters : 16
N/A% (0 of 18) |                         | Elapsed Time: 0:00:00 ETA:  --:--:--

========== Performance occupancy ==========
Preq Accuracy:  70.53 (+/-) 1.33
F1 score:  0.66 (+/-) 0.04
Precision:  0.68 (+/-) 0.02
Recall:  0.71 (+/-) 0.01
Training time:  2.01 (+/-) 0.0
Testing time:  0.0 (+/-) 0.0


========== Network ==========
Number of hidden layers:  1.0 (+/-) 0.0
Number of features:  10.8 (+/-) 2.93
Infinite Delay
100% (18 of 18) |########################| Elapsed Time: 0:00:31 ETA:  00:00:00

=== Performance result ===
Accuracy:  68.61764705882354 (+/-) 4.071888605623808
Precision:  0.7218940864960282
Recall:  0.6861764705882353
F1 score:  0.5587592918706882
Testing Time:  0.001752166187061983 (+/-) 0.00042336070587403
Training Time:  1.648672244128059 (+/-) 0.02541755038935055


=== Average network evolution ===
Total hidden node:  10.88888888888889 (+/-) 10.88888888888889


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=11, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 11
No. of parameters : 107

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=11, out_features=2, bias=True)
)
No. of inputs : 11
No. of output : 2
No. of parameters : 24
100% (18 of 18) |########################| Elapsed Time: 0:00:31 ETA:  00:00:00

=== Performance result ===
Accuracy:  68.67058823529412 (+/-) 4.167629415878635
Precision:  0.6442047985640439
Recall:  0.6867058823529412
F1 score:  0.5656881472183504
Testing Time:  0.0015804767608642578 (+/-) 0.0005966667818032134
Training Time:  1.6411755084991455 (+/-) 0.015749832669608207


=== Average network evolution ===
Total hidden node:  8.166666666666666 (+/-) 8.166666666666666


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=9, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 9
No. of parameters : 89

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=9, out_features=2, bias=True)
)
No. of inputs : 9
No. of output : 2
No. of parameters : 20
100% (18 of 18) |########################| Elapsed Time: 0:00:31 ETA:  00:00:00

=== Performance result ===
Accuracy:  68.6058823529412 (+/-) 4.11946178498161
Precision:  0.6590537216828479
Recall:  0.6860588235294117
F1 score:  0.5585938782968816
Testing Time:  0.001628553166108973 (+/-) 0.0004705479159420442
Training Time:  1.6872956893023323 (+/-) 0.023702669294865565


=== Average network evolution ===
Total hidden node:  11.722222222222221 (+/-) 11.722222222222221


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=12, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 12
No. of parameters : 116

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=12, out_features=2, bias=True)
)
No. of inputs : 12
No. of output : 2
No. of parameters : 26
100% (18 of 18) |########################| Elapsed Time: 0:00:31 ETA:  00:00:00

=== Performance result ===
Accuracy:  68.28235294117648 (+/-) 3.968143037939808
Precision:  0.6076107173798099
Recall:  0.6828235294117647
F1 score:  0.5734919569935745
Testing Time:  0.0016302080715403838 (+/-) 0.00048178200675731263
Training Time:  1.643831491470337 (+/-) 0.015034646758235857


=== Average network evolution ===
Total hidden node:  12.833333333333334 (+/-) 12.833333333333334


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=13, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 13
No. of parameters : 125

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=13, out_features=2, bias=True)
)
No. of inputs : 13
No. of output : 2
No. of parameters : 28
100% (18 of 18) |########################| Elapsed Time: 0:00:31 ETA:  00:00:00

=== Performance result ===
Accuracy:  63.458823529411774 (+/-) 4.407888493242329
Precision:  0.6276336545183165
Recall:  0.6345882352941177
F1 score:  0.6308172086354512
Testing Time:  0.001984694424797507 (+/-) 0.00048360878721759
Training Time:  1.669492988025441 (+/-) 0.06746450995347832


=== Average network evolution ===
Total hidden node:  11.777777777777779 (+/-) 11.777777777777779


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=12, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 12
No. of parameters : 116

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=12, out_features=2, bias=True)
)
No. of inputs : 12
No. of output : 2
No. of parameters : 26

========== Performance occupancy ==========
Preq Accuracy:  67.53 (+/-) 2.04
F1 score:  0.58 (+/-) 0.03
Precision:  0.65 (+/-) 0.04
Recall:  0.68 (+/-) 0.02
Training time:  1.66 (+/-) 0.02
Testing time:  0.0 (+/-) 0.0


========== Network ==========
Number of hidden layers:  1.0 (+/-) 0.0
Number of features:  11.4 (+/-) 1.36
In [4]:
%run DEVDAN_rfid.ipynb
Number of input:  3
Number of output:  4
Number of batch:  280
All Data
100% (280 of 280) |######################| Elapsed Time: 0:14:38 ETA:  00:00:00

=== Performance result ===
Accuracy:  99.16200716845877 (+/-) 2.3856480045015664
Precision:  0.9916305545280637
Recall:  0.9916200716845878
F1 score:  0.9916086973596855
Testing Time:  0.001957467807236538 (+/-) 0.0008929287337201698
Training Time:  3.1446892078632094 (+/-) 0.05948944583883505


=== Average network evolution ===
Total hidden node:  56.746428571428574 (+/-) 9.87366562929815


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=3, out_features=63, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 3
No. of nodes : 63
No. of parameters : 255

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=63, out_features=4, bias=True)
)
No. of inputs : 63
No. of output : 4
No. of parameters : 256
100% (280 of 280) |######################| Elapsed Time: 0:14:39 ETA:  00:00:00

=== Performance result ===
Accuracy:  99.20860215053763 (+/-) 2.739999316405423
Precision:  0.9920817445976162
Recall:  0.9920860215053764
F1 score:  0.9920798790492309
Testing Time:  0.0019417449992190125 (+/-) 0.0005426591468695644
Training Time:  3.1491071545522273 (+/-) 0.040680363804178735


=== Average network evolution ===
Total hidden node:  60.357142857142854 (+/-) 10.702517346448003


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=3, out_features=65, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 3
No. of nodes : 65
No. of parameters : 263

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=65, out_features=4, bias=True)
)
No. of inputs : 65
No. of output : 4
No. of parameters : 264
100% (280 of 280) |######################| Elapsed Time: 0:14:38 ETA:  00:00:00

=== Performance result ===
Accuracy:  98.90537634408602 (+/-) 4.2741961182111705
Precision:  0.9890584415947367
Recall:  0.9890537634408603
F1 score:  0.9890468781008143
Testing Time:  0.0018783752208969499 (+/-) 0.0004986310746219353
Training Time:  3.143739750735649 (+/-) 0.04479412162251396


=== Average network evolution ===
Total hidden node:  64.51428571428572 (+/-) 13.559649023210484


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=3, out_features=73, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 3
No. of nodes : 73
No. of parameters : 295

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=73, out_features=4, bias=True)
)
No. of inputs : 73
No. of output : 4
No. of parameters : 296
100% (280 of 280) |######################| Elapsed Time: 0:14:38 ETA:  00:00:00

=== Performance result ===
Accuracy:  99.22078853046594 (+/-) 1.8266441276014085
Precision:  0.9922022505416935
Recall:  0.9922078853046595
F1 score:  0.9922010427154767
Testing Time:  0.0019096636003063572 (+/-) 0.0015309608370982178
Training Time:  3.1443920588407894 (+/-) 0.053524463308117755


=== Average network evolution ===
Total hidden node:  59.917857142857144 (+/-) 9.925636128280162


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=3, out_features=65, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 3
No. of nodes : 65
No. of parameters : 263

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=65, out_features=4, bias=True)
)
No. of inputs : 65
No. of output : 4
No. of parameters : 264
100% (280 of 280) |######################| Elapsed Time: 0:14:42 ETA:  00:00:00

=== Performance result ===
Accuracy:  99.26594982078855 (+/-) 1.7951612813772146
Precision:  0.9926561145859011
Recall:  0.9926594982078853
F1 score:  0.9926516957440156
Testing Time:  0.00179285644203104 (+/-) 0.000505124277207529
Training Time:  3.1589536316505895 (+/-) 0.047892787624809585


=== Average network evolution ===
Total hidden node:  58.19642857142857 (+/-) 9.986812094774114


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=3, out_features=64, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 3
No. of nodes : 64
No. of parameters : 259

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=64, out_features=4, bias=True)
)
No. of inputs : 64
No. of output : 4
No. of parameters : 260

========== Performance occupancy ==========
Preq Accuracy:  99.15 (+/-) 0.13
F1 score:  0.99 (+/-) 0.0
Precision:  0.99 (+/-) 0.0
Recall:  0.99 (+/-) 0.0
Training time:  3.15 (+/-) 0.01
Testing time:  0.0 (+/-) 0.0


========== Network ==========
Number of hidden layers:  1.0 (+/-) 0.0
Number of features:  66.0 (+/-) 3.58
50% Data
100% (280 of 280) |######################| Elapsed Time: 0:11:09 ETA:  00:00:00

=== Performance result ===
Accuracy:  98.67347670250895 (+/-) 4.41665296309441
Precision:  0.9867210092793409
Recall:  0.9867347670250896
F1 score:  0.986718382713746
Testing Time:  0.0018220904907445326 (+/-) 0.000548616112128294
Training Time:  2.396297507815891 (+/-) 0.035531816971533674


=== Average network evolution ===
Total hidden node:  53.61071428571429 (+/-) 12.635631005943761


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=3, out_features=61, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 3
No. of nodes : 61
No. of parameters : 247

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=61, out_features=4, bias=True)
)
No. of inputs : 61
No. of output : 4
No. of parameters : 248
100% (280 of 280) |######################| Elapsed Time: 0:11:09 ETA:  00:00:00

=== Performance result ===
Accuracy:  97.9010752688172 (+/-) 8.435249830562935
Precision:  0.9790886190266312
Recall:  0.9790107526881721
F1 score:  0.9789715977410168
Testing Time:  0.0019059899032756846 (+/-) 0.0004774420152486833
Training Time:  2.396136726529795 (+/-) 0.030635057666078932


=== Average network evolution ===
Total hidden node:  57.003571428571426 (+/-) 14.776549523360536


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=3, out_features=68, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 3
No. of nodes : 68
No. of parameters : 275

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=68, out_features=4, bias=True)
)
No. of inputs : 68
No. of output : 4
No. of parameters : 276
100% (280 of 280) |######################| Elapsed Time: 0:11:10 ETA:  00:00:00

=== Performance result ===
Accuracy:  98.39784946236558 (+/-) 6.626145321889703
Precision:  0.9839858995223008
Recall:  0.9839784946236559
F1 score:  0.9839664371313739
Testing Time:  0.0018169991004424284 (+/-) 0.0005103784658928544
Training Time:  2.3986312685046998 (+/-) 0.028100286029922046


=== Average network evolution ===
Total hidden node:  54.75714285714286 (+/-) 12.518769581581678


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=3, out_features=62, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 3
No. of nodes : 62
No. of parameters : 251

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=62, out_features=4, bias=True)
)
No. of inputs : 62
No. of output : 4
No. of parameters : 252
100% (280 of 280) |######################| Elapsed Time: 0:11:12 ETA:  00:00:00

=== Performance result ===
Accuracy:  98.83225806451614 (+/-) 3.654000447989094
Precision:  0.9883399507157558
Recall:  0.9883225806451613
F1 score:  0.9883024013059986
Testing Time:  0.0018657774908140995 (+/-) 0.0006024151503329402
Training Time:  2.4049223580240775 (+/-) 0.06540753316067224


=== Average network evolution ===
Total hidden node:  54.15357142857143 (+/-) 12.410594038471933


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=3, out_features=63, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 3
No. of nodes : 63
No. of parameters : 255

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=63, out_features=4, bias=True)
)
No. of inputs : 63
No. of output : 4
No. of parameters : 256
100% (280 of 280) |######################| Elapsed Time: 0:11:08 ETA:  00:00:00

=== Performance result ===
Accuracy:  98.71971326164875 (+/-) 4.935563858242005
Precision:  0.9871943743448504
Recall:  0.9871971326164874
F1 score:  0.9871784102238991
Testing Time:  0.0017406966096611433 (+/-) 0.0005074713731817038
Training Time:  2.3918756028657318 (+/-) 0.029083390457963352


=== Average network evolution ===
Total hidden node:  50.94642857142857 (+/-) 12.710821658921107


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=3, out_features=59, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 3
No. of nodes : 59
No. of parameters : 239

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=59, out_features=4, bias=True)
)
No. of inputs : 59
No. of output : 4
No. of parameters : 240

========== Performance occupancy ==========
Preq Accuracy:  98.5 (+/-) 0.33
F1 score:  0.99 (+/-) 0.0
Precision:  0.99 (+/-) 0.0
Recall:  0.99 (+/-) 0.0
Training time:  2.4 (+/-) 0.0
Testing time:  0.0 (+/-) 0.0


========== Network ==========
Number of hidden layers:  1.0 (+/-) 0.0
Number of features:  62.6 (+/-) 3.01
25% Data
100% (280 of 280) |######################| Elapsed Time: 0:09:25 ETA:  00:00:00

=== Performance result ===
Accuracy:  98.16594982078851 (+/-) 6.590583736689308
Precision:  0.9816542274176899
Recall:  0.9816594982078853
F1 score:  0.9816565922866788
Testing Time:  0.0017446642708180199 (+/-) 0.0005250061664078484
Training Time:  2.020343662590109 (+/-) 0.031853494458596344


=== Average network evolution ===
Total hidden node:  45.65714285714286 (+/-) 14.114213417975627


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=3, out_features=57, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 3
No. of nodes : 57
No. of parameters : 231

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=57, out_features=4, bias=True)
)
No. of inputs : 57
No. of output : 4
No. of parameters : 232
100% (280 of 280) |######################| Elapsed Time: 0:09:24 ETA:  00:00:00

=== Performance result ===
Accuracy:  98.15017921146952 (+/-) 7.082468003067731
Precision:  0.981488406246896
Recall:  0.9815017921146953
F1 score:  0.9814904683512408
Testing Time:  0.001727890370139939 (+/-) 0.0005045927592710244
Training Time:  2.0179740750234187 (+/-) 0.021743633146465043


=== Average network evolution ===
Total hidden node:  45.22142857142857 (+/-) 13.783306599518365


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=3, out_features=57, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 3
No. of nodes : 57
No. of parameters : 231

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=57, out_features=4, bias=True)
)
No. of inputs : 57
No. of output : 4
No. of parameters : 232
100% (280 of 280) |######################| Elapsed Time: 0:09:28 ETA:  00:00:00

=== Performance result ===
Accuracy:  98.65412186379929 (+/-) 4.138503859250891
Precision:  0.986524291344413
Recall:  0.9865412186379928
F1 score:  0.9865280841625699
Testing Time:  0.0018045987706885116 (+/-) 0.0004970554946503682
Training Time:  2.0328311638165544 (+/-) 0.030140800660536107


=== Average network evolution ===
Total hidden node:  47.17142857142857 (+/-) 12.69754917698848


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=3, out_features=59, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 3
No. of nodes : 59
No. of parameters : 239

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=59, out_features=4, bias=True)
)
No. of inputs : 59
No. of output : 4
No. of parameters : 240
100% (280 of 280) |######################| Elapsed Time: 0:09:28 ETA:  00:00:00

=== Performance result ===
Accuracy:  98.34767025089606 (+/-) 5.5838528038436985
Precision:  0.9834726024723873
Recall:  0.9834767025089606
F1 score:  0.9834384045488033
Testing Time:  0.0017111925241340446 (+/-) 0.0004989632509568414
Training Time:  2.031305744656525 (+/-) 0.030469042538728366


=== Average network evolution ===
Total hidden node:  46.01428571428571 (+/-) 12.231391530627667


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=3, out_features=57, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 3
No. of nodes : 57
No. of parameters : 231

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=57, out_features=4, bias=True)
)
No. of inputs : 57
No. of output : 4
No. of parameters : 232
100% (280 of 280) |######################| Elapsed Time: 0:09:26 ETA:  00:00:00

=== Performance result ===
Accuracy:  98.468458781362 (+/-) 4.7735616112276515
Precision:  0.984667108653198
Recall:  0.9846845878136201
F1 score:  0.9846685460334352
Testing Time:  0.0019368065728081597 (+/-) 0.003451441668091678
Training Time:  2.0254308382670083 (+/-) 0.0474238403005755


=== Average network evolution ===
Total hidden node:  40.92142857142857 (+/-) 11.315329587487472


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=3, out_features=51, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 3
No. of nodes : 51
No. of parameters : 207

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=51, out_features=4, bias=True)
)
No. of inputs : 51
No. of output : 4
No. of parameters : 208
N/A% (0 of 280) |                        | Elapsed Time: 0:00:00 ETA:  --:--:--

========== Performance occupancy ==========
Preq Accuracy:  98.36 (+/-) 0.19
F1 score:  0.98 (+/-) 0.0
Precision:  0.98 (+/-) 0.0
Recall:  0.98 (+/-) 0.0
Training time:  2.03 (+/-) 0.01
Testing time:  0.0 (+/-) 0.0


========== Network ==========
Number of hidden layers:  1.0 (+/-) 0.0
Number of features:  56.2 (+/-) 2.71
Infinite Delay
100% (280 of 280) |######################| Elapsed Time: 0:07:44 ETA:  00:00:00

=== Performance result ===
Accuracy:  31.410394265232974 (+/-) 9.706964550077153
C:\Users\SCSE\AppData\Local\Continuum\miniconda3\envs\stmicro\lib\site-packages\sklearn\metrics\_classification.py:1221: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
Precision:  0.34188549776389554
Recall:  0.31410394265232977
F1 score:  0.2017385057028227
Testing Time:  0.0015167215818999917 (+/-) 0.0005152670757772471
Training Time:  1.6487033358611514 (+/-) 0.0353181638411217


=== Average network evolution ===
Total hidden node:  7.7785714285714285 (+/-) 7.7785714285714285


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=3, out_features=9, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 3
No. of nodes : 9
No. of parameters : 39

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=9, out_features=4, bias=True)
)
No. of inputs : 9
No. of output : 4
No. of parameters : 40
100% (280 of 280) |######################| Elapsed Time: 0:07:54 ETA:  00:00:00

=== Performance result ===
Accuracy:  52.41720430107527 (+/-) 7.246118085534872
Precision:  0.4135975469002727
Recall:  0.5241720430107527
F1 score:  0.44654189939745154
Testing Time:  0.0014444363159945362 (+/-) 0.0005333543502286279
Training Time:  1.683700058195326 (+/-) 0.07182905324917416


=== Average network evolution ===
Total hidden node:  6.9714285714285715 (+/-) 6.9714285714285715


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=3, out_features=6, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 3
No. of nodes : 6
No. of parameters : 27

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=6, out_features=4, bias=True)
)
No. of inputs : 6
No. of output : 4
No. of parameters : 28
100% (280 of 280) |######################| Elapsed Time: 0:07:45 ETA:  00:00:00

=== Performance result ===
Accuracy:  39.24910394265233 (+/-) 4.554841953195149
Precision:  0.43445530392104825
Recall:  0.3924910394265233
F1 score:  0.30389192686221667
Testing Time:  0.0014920311589394846 (+/-) 0.0005200306165009971
Training Time:  1.652131998410789 (+/-) 0.03426592415383448


=== Average network evolution ===
Total hidden node:  9.153571428571428 (+/-) 9.153571428571428


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=3, out_features=9, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 3
No. of nodes : 9
No. of parameters : 39

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=9, out_features=4, bias=True)
)
No. of inputs : 9
No. of output : 4
No. of parameters : 40
100% (280 of 280) |######################| Elapsed Time: 0:07:44 ETA:  00:00:00

=== Performance result ===
Accuracy:  34.983870967741936 (+/-) 4.526274318814219
Precision:  0.4266029024844088
Recall:  0.34983870967741937
F1 score:  0.32155222104565057
Testing Time:  0.0014608983070619644 (+/-) 0.0005224629804787121
Training Time:  1.6477424824964189 (+/-) 0.023482086403910286


=== Average network evolution ===
Total hidden node:  8.128571428571428 (+/-) 8.128571428571428


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=3, out_features=8, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 3
No. of nodes : 8
No. of parameters : 35

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=8, out_features=4, bias=True)
)
No. of inputs : 8
No. of output : 4
No. of parameters : 36
100% (280 of 280) |######################| Elapsed Time: 0:07:44 ETA:  00:00:00

=== Performance result ===
Accuracy:  51.445519713261646 (+/-) 4.475905987318934
Precision:  0.6126508207389302
Recall:  0.5144551971326164
F1 score:  0.43742845272802844
Testing Time:  0.0015578680140997773 (+/-) 0.0022953760685736142
Training Time:  1.650023498842793 (+/-) 0.025702613646082263


=== Average network evolution ===
Total hidden node:  13.989285714285714 (+/-) 13.989285714285714


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=3, out_features=14, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 3
No. of nodes : 14
No. of parameters : 59

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=14, out_features=4, bias=True)
)
No. of inputs : 14
No. of output : 4
No. of parameters : 60

========== Performance occupancy ==========
Preq Accuracy:  41.9 (+/-) 8.56
F1 score:  0.34 (+/-) 0.09
Precision:  0.45 (+/-) 0.09
Recall:  0.42 (+/-) 0.09
Training time:  1.66 (+/-) 0.01
Testing time:  0.0 (+/-) 0.0


========== Network ==========
Number of hidden layers:  1.0 (+/-) 0.0
Number of features:  9.2 (+/-) 2.64
In [5]:
%run DEVDAN_occupancy.ipynb
Number of input:  5
Number of output:  2
Number of batch:  20
All Data
100% (20 of 20) |########################| Elapsed Time: 0:00:59 ETA:  00:00:00

=== Performance result ===
Accuracy:  94.12631578947368 (+/-) 12.167681183116247
Precision:  0.9417026075418174
Recall:  0.9412631578947368
F1 score:  0.9392022982421169
Testing Time:  0.001730053048384817 (+/-) 0.0004345990837267352
Training Time:  3.1115188347665885 (+/-) 0.02442550053832812


=== Average network evolution ===
Total hidden node:  28.25 (+/-) 11.932623349456732


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=5, out_features=44, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 5
No. of nodes : 44
No. of parameters : 269

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=44, out_features=2, bias=True)
)
No. of inputs : 44
No. of output : 2
No. of parameters : 90
100% (20 of 20) |########################| Elapsed Time: 0:01:00 ETA:  00:00:00

=== Performance result ===
Accuracy:  93.81052631578946 (+/-) 12.164049478812215
Precision:  0.9382032792867195
Recall:  0.9381052631578948
F1 score:  0.9359791678273631
Testing Time:  0.0019296093990928249 (+/-) 0.0003916776449929711
Training Time:  3.159525996760318 (+/-) 0.052620773895586975


=== Average network evolution ===
Total hidden node:  49.5 (+/-) 12.031209415515965


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=5, out_features=66, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 5
No. of nodes : 66
No. of parameters : 401

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=66, out_features=2, bias=True)
)
No. of inputs : 66
No. of output : 2
No. of parameters : 134
100% (20 of 20) |########################| Elapsed Time: 0:00:59 ETA:  00:00:00

=== Performance result ===
Accuracy:  91.48947368421054 (+/-) 12.658340073137639
Precision:  0.9129173208274038
Recall:  0.9148947368421053
F1 score:  0.9130112959570756
Testing Time:  0.0017166765112625925 (+/-) 0.0005482329221608689
Training Time:  3.138629072590878 (+/-) 0.04074785126466747


=== Average network evolution ===
Total hidden node:  31.9 (+/-) 11.022250223978768


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=5, out_features=47, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 5
No. of nodes : 47
No. of parameters : 287

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=47, out_features=2, bias=True)
)
No. of inputs : 47
No. of output : 2
No. of parameters : 96
100% (20 of 20) |########################| Elapsed Time: 0:00:59 ETA:  00:00:00

=== Performance result ===
Accuracy:  94.10526315789473 (+/-) 12.20769704063838
Precision:  0.940918058689336
Recall:  0.9410526315789474
F1 score:  0.9392777195936105
Testing Time:  0.0016643248106303968 (+/-) 0.0005660011983113068
Training Time:  3.1298930394022086 (+/-) 0.028842353283985152


=== Average network evolution ===
Total hidden node:  44.85 (+/-) 12.426886174742247


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=5, out_features=61, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 5
No. of nodes : 61
No. of parameters : 371

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=61, out_features=2, bias=True)
)
No. of inputs : 61
No. of output : 2
No. of parameters : 124
100% (20 of 20) |########################| Elapsed Time: 0:00:59 ETA:  00:00:00

=== Performance result ===
Accuracy:  92.38421052631578 (+/-) 13.75856721265526
Precision:  0.924750514932838
Recall:  0.9238421052631579
F1 score:  0.9200112410838851
Testing Time:  0.0017785524067125823 (+/-) 0.0005197186644303318
Training Time:  3.1248184003328023 (+/-) 0.024422274058000282


=== Average network evolution ===
Total hidden node:  40.9 (+/-) 12.93792873685738


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=5, out_features=58, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 5
No. of nodes : 58
No. of parameters : 353

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=58, out_features=2, bias=True)
)
No. of inputs : 58
No. of output : 2
No. of parameters : 118

========== Performance occupancy ==========
Preq Accuracy:  93.18 (+/-) 1.06
F1 score:  0.93 (+/-) 0.01
Precision:  0.93 (+/-) 0.01
Recall:  0.93 (+/-) 0.01
Training time:  3.13 (+/-) 0.02
Testing time:  0.0 (+/-) 0.0


========== Network ==========
Number of hidden layers:  1.0 (+/-) 0.0
Number of features:  55.2 (+/-) 8.38
50% Data
100% (20 of 20) |########################| Elapsed Time: 0:00:45 ETA:  00:00:00

=== Performance result ===
Accuracy:  87.60526315789473 (+/-) 16.072515726321537
Precision:  0.872243696469172
Recall:  0.8760526315789474
F1 score:  0.8733691977334447
Testing Time:  0.001734093615883275 (+/-) 0.0005333696538404918
Training Time:  2.3769333864513196 (+/-) 0.006202818252542381


=== Average network evolution ===
Total hidden node:  38.45 (+/-) 12.839295151993353


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=5, out_features=55, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 5
No. of nodes : 55
No. of parameters : 335

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=55, out_features=2, bias=True)
)
No. of inputs : 55
No. of output : 2
No. of parameters : 112
100% (20 of 20) |########################| Elapsed Time: 0:00:45 ETA:  00:00:00

=== Performance result ===
Accuracy:  91.91052631578947 (+/-) 12.283274667819528
Precision:  0.9173429821100337
Recall:  0.9191052631578948
F1 score:  0.917408148397425
Testing Time:  0.0016140435871325042 (+/-) 0.0004898602271977422
Training Time:  2.3798038081118933 (+/-) 0.013616793705851036


=== Average network evolution ===
Total hidden node:  32.3 (+/-) 10.654107189248661


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=5, out_features=46, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 5
No. of nodes : 46
No. of parameters : 281

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=46, out_features=2, bias=True)
)
No. of inputs : 46
No. of output : 2
No. of parameters : 94
100% (20 of 20) |########################| Elapsed Time: 0:00:45 ETA:  00:00:00

=== Performance result ===
Accuracy:  87.36842105263158 (+/-) 17.672460068574104
Precision:  0.8700473239695742
Recall:  0.8736842105263158
F1 score:  0.8643250802029355
Testing Time:  0.0018304147218403063 (+/-) 0.0005872034986080351
Training Time:  2.3866209230924906 (+/-) 0.021451343352490174


=== Average network evolution ===
Total hidden node:  31.65 (+/-) 12.301524295793591


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=5, out_features=46, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 5
No. of nodes : 46
No. of parameters : 281

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=46, out_features=2, bias=True)
)
No. of inputs : 46
No. of output : 2
No. of parameters : 94
100% (20 of 20) |########################| Elapsed Time: 0:00:45 ETA:  00:00:00

=== Performance result ===
Accuracy:  87.89473684210527 (+/-) 14.350773816811211
Precision:  0.8749488467663327
Recall:  0.8789473684210526
F1 score:  0.8715753736179883
Testing Time:  0.0015674013840524775 (+/-) 0.0004904560890028188
Training Time:  2.3863525641591927 (+/-) 0.02658769584352912


=== Average network evolution ===
Total hidden node:  26.3 (+/-) 11.506954418958998


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=5, out_features=41, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 5
No. of nodes : 41
No. of parameters : 251

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=41, out_features=2, bias=True)
)
No. of inputs : 41
No. of output : 2
No. of parameters : 84
100% (20 of 20) |########################| Elapsed Time: 0:00:45 ETA:  00:00:00

=== Performance result ===
Accuracy:  87.34210526315789 (+/-) 17.994452823300083
Precision:  0.869182135321153
Recall:  0.873421052631579
F1 score:  0.8647136210766404
Testing Time:  0.001662982137579667 (+/-) 0.0005698806249189355
Training Time:  2.3986512485303377 (+/-) 0.035002228841415406


=== Average network evolution ===
Total hidden node:  33.25 (+/-) 12.259180233604528


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=5, out_features=49, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 5
No. of nodes : 49
No. of parameters : 299

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=49, out_features=2, bias=True)
)
No. of inputs : 49
No. of output : 2
No. of parameters : 100

========== Performance occupancy ==========
Preq Accuracy:  88.42 (+/-) 1.75
F1 score:  0.88 (+/-) 0.02
Precision:  0.88 (+/-) 0.02
Recall:  0.88 (+/-) 0.02
Training time:  2.39 (+/-) 0.01
Testing time:  0.0 (+/-) 0.0


========== Network ==========
Number of hidden layers:  1.0 (+/-) 0.0
Number of features:  47.4 (+/-) 4.59
25% Data
100% (20 of 20) |########################| Elapsed Time: 0:00:38 ETA:  00:00:00

=== Performance result ===
Accuracy:  91.0 (+/-) 13.084703805750076
Precision:  0.9095697739830984
Recall:  0.91
F1 score:  0.9097721917869059
Testing Time:  0.0017238541653281764 (+/-) 0.00043059539875961694
Training Time:  2.042232450686003 (+/-) 0.04117742082942164


=== Average network evolution ===
Total hidden node:  27.05 (+/-) 8.605085705558079


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=5, out_features=40, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 5
No. of nodes : 40
No. of parameters : 245

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=40, out_features=2, bias=True)
)
No. of inputs : 40
No. of output : 2
No. of parameters : 82
100% (20 of 20) |########################| Elapsed Time: 0:00:38 ETA:  00:00:00

=== Performance result ===
Accuracy:  89.41578947368419 (+/-) 13.440130918766133
Precision:  0.8918804902691551
Recall:  0.8941578947368422
F1 score:  0.8926570755427262
Testing Time:  0.0016226015592876234 (+/-) 0.0005843436607858528
Training Time:  2.0351304756967643 (+/-) 0.029165551791218214


=== Average network evolution ===
Total hidden node:  21.0 (+/-) 8.573214099741124


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=5, out_features=33, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 5
No. of nodes : 33
No. of parameters : 203

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=33, out_features=2, bias=True)
)
No. of inputs : 33
No. of output : 2
No. of parameters : 68
100% (20 of 20) |########################| Elapsed Time: 0:00:38 ETA:  00:00:00

=== Performance result ===
Accuracy:  86.09473684210526 (+/-) 16.149155874443213
Precision:  0.8541025071575736
Recall:  0.8609473684210527
F1 score:  0.8535046581699114
Testing Time:  0.001569358926070364 (+/-) 0.0004944556420625095
Training Time:  2.032375875272249 (+/-) 0.02918430322289312


=== Average network evolution ===
Total hidden node:  25.05 (+/-) 7.003392035292612


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=5, out_features=35, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 5
No. of nodes : 35
No. of parameters : 215

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=35, out_features=2, bias=True)
)
No. of inputs : 35
No. of output : 2
No. of parameters : 72
100% (20 of 20) |########################| Elapsed Time: 0:00:38 ETA:  00:00:00

=== Performance result ===
Accuracy:  86.69473684210526 (+/-) 17.53677260364063
Precision:  0.8613312539315904
Recall:  0.8669473684210526
F1 score:  0.8582285895025581
Testing Time:  0.0017787280835603412 (+/-) 0.00041543628684626585
Training Time:  2.0263755321502686 (+/-) 0.03199586071753423


=== Average network evolution ===
Total hidden node:  28.2 (+/-) 10.380751417888783


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=5, out_features=41, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 5
No. of nodes : 41
No. of parameters : 251

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=41, out_features=2, bias=True)
)
No. of inputs : 41
No. of output : 2
No. of parameters : 84
100% (20 of 20) |########################| Elapsed Time: 0:00:38 ETA:  00:00:00

=== Performance result ===
Accuracy:  84.62631578947368 (+/-) 15.846628135622357
Precision:  0.8378515269468836
Recall:  0.8462631578947368
F1 score:  0.8389896876223986
Testing Time:  0.0017660918988679584 (+/-) 0.0005190602958871454
Training Time:  2.0120899049859298 (+/-) 0.01363160559605076


=== Average network evolution ===
Total hidden node:  29.6 (+/-) 11.547294055318762


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=5, out_features=44, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 5
No. of nodes : 44
No. of parameters : 269

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=44, out_features=2, bias=True)
)
No. of inputs : 44
No. of output : 2
No. of parameters : 90
N/A% (0 of 20) |                         | Elapsed Time: 0:00:00 ETA:  --:--:--

========== Performance occupancy ==========
Preq Accuracy:  87.57 (+/-) 2.31
F1 score:  0.87 (+/-) 0.03
Precision:  0.87 (+/-) 0.03
Recall:  0.88 (+/-) 0.02
Training time:  2.03 (+/-) 0.01
Testing time:  0.0 (+/-) 0.0


========== Network ==========
Number of hidden layers:  1.0 (+/-) 0.0
Number of features:  38.6 (+/-) 4.03
Infinite Delay
100% (20 of 20) |########################| Elapsed Time: 0:00:34 ETA:  00:00:00

=== Performance result ===
Accuracy:  91.37894736842105 (+/-) 11.173068133845138
Precision:  0.9163031494420744
Recall:  0.9137894736842105
F1 score:  0.9080525272733756
Testing Time:  0.0016627060739617598 (+/-) 0.0005659536710162378
Training Time:  1.6492875249762284 (+/-) 0.025503638534587997


=== Average network evolution ===
Total hidden node:  14.0 (+/-) 14.0


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=5, out_features=14, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 5
No. of nodes : 14
No. of parameters : 89

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=14, out_features=2, bias=True)
)
No. of inputs : 14
No. of output : 2
No. of parameters : 30
100% (20 of 20) |########################| Elapsed Time: 0:00:36 ETA:  00:00:00

=== Performance result ===
Accuracy:  91.4842105263158 (+/-) 12.722845724290604
Precision:  0.9169503406266513
Recall:  0.9148421052631579
F1 score:  0.9094121978720788
Testing Time:  0.0016207318556936163 (+/-) 0.0005768451525426626
Training Time:  1.7520778806586015 (+/-) 0.10397831349668323


=== Average network evolution ===
Total hidden node:  14.9 (+/-) 14.9


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=5, out_features=15, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 5
No. of nodes : 15
No. of parameters : 95

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=15, out_features=2, bias=True)
)
No. of inputs : 15
No. of output : 2
No. of parameters : 32
100% (20 of 20) |########################| Elapsed Time: 0:00:34 ETA:  00:00:00

=== Performance result ===
Accuracy:  94.70526315789473 (+/-) 5.304960308816303
Precision:  0.9473117368341452
Recall:  0.9470526315789474
F1 score:  0.9471711677484661
Testing Time:  0.0017188222784745065 (+/-) 0.0005392224086763533
Training Time:  1.6505292591295744 (+/-) 0.018209329865814614


=== Average network evolution ===
Total hidden node:  20.85 (+/-) 20.85


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=5, out_features=21, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 5
No. of nodes : 21
No. of parameters : 131

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=21, out_features=2, bias=True)
)
No. of inputs : 21
No. of output : 2
No. of parameters : 44
100% (20 of 20) |########################| Elapsed Time: 0:00:34 ETA:  00:00:00

=== Performance result ===
Accuracy:  92.78421052631579 (+/-) 9.36484260456684
Precision:  0.9301252196977988
Recall:  0.9278421052631579
F1 score:  0.9238726997525788
Testing Time:  0.001508173189665142 (+/-) 0.0005970647588017396
Training Time:  1.648397633903905 (+/-) 0.010864549638751405


=== Average network evolution ===
Total hidden node:  14.8 (+/-) 14.8


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=5, out_features=15, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 5
No. of nodes : 15
No. of parameters : 95

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=15, out_features=2, bias=True)
)
No. of inputs : 15
No. of output : 2
No. of parameters : 32
100% (20 of 20) |########################| Elapsed Time: 0:00:34 ETA:  00:00:00

=== Performance result ===
Accuracy:  90.29473684210525 (+/-) 13.747668651513266
Precision:  0.907797686145002
Recall:  0.9029473684210526
F1 score:  0.8946544769148023
Testing Time:  0.0017725793938887747 (+/-) 0.000697708214450811
Training Time:  1.6471675571642423 (+/-) 0.00993062416170704


=== Average network evolution ===
Total hidden node:  15.0 (+/-) 15.0


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=5, out_features=15, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 5
No. of nodes : 15
No. of parameters : 95

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=15, out_features=2, bias=True)
)
No. of inputs : 15
No. of output : 2
No. of parameters : 32

========== Performance occupancy ==========
Preq Accuracy:  92.13 (+/-) 1.51
F1 score:  0.92 (+/-) 0.02
Precision:  0.92 (+/-) 0.01
Recall:  0.92 (+/-) 0.02
Training time:  1.67 (+/-) 0.04
Testing time:  0.0 (+/-) 0.0


========== Network ==========
Number of hidden layers:  1.0 (+/-) 0.0
Number of features:  16.0 (+/-) 2.53
In [6]:
%run DEVDAN_creditcarddefault.ipynb
Number of input:  24
Number of output:  2
Number of batch:  30
All Data
100% (30 of 30) |########################| Elapsed Time: 0:01:31 ETA:  00:00:00

=== Performance result ===
Accuracy:  79.27931034482758 (+/-) 4.68279163057788
Precision:  0.7618905682479733
Recall:  0.7927931034482759
F1 score:  0.7569161211148352
Testing Time:  0.0024629214714313374 (+/-) 0.0006169476935006807
Training Time:  3.1432375743471344 (+/-) 0.03728141552273546


=== Average network evolution ===
Total hidden node:  22.766666666666666 (+/-) 0.42295258468165065


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=24, out_features=23, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 24
No. of nodes : 23
No. of parameters : 599

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=23, out_features=2, bias=True)
)
No. of inputs : 23
No. of output : 2
No. of parameters : 48
100% (30 of 30) |########################| Elapsed Time: 0:01:30 ETA:  00:00:00

=== Performance result ===
Accuracy:  79.9896551724138 (+/-) 2.665920922280433
Precision:  0.7806855217681604
Recall:  0.799896551724138
F1 score:  0.7498974932146996
Testing Time:  0.002342372105039399 (+/-) 0.0006770066891784815
Training Time:  3.124590010478579 (+/-) 0.05100577509587114


=== Average network evolution ===
Total hidden node:  8.4 (+/-) 0.6110100926607787


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=24, out_features=9, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 24
No. of nodes : 9
No. of parameters : 249

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=9, out_features=2, bias=True)
)
No. of inputs : 9
No. of output : 2
No. of parameters : 20
100% (30 of 30) |########################| Elapsed Time: 0:01:31 ETA:  00:00:00

=== Performance result ===
Accuracy:  80.18275862068967 (+/-) 2.450062485553243
Precision:  0.7816316554281255
Recall:  0.8018275862068965
F1 score:  0.7562892714526392
Testing Time:  0.0025006080495900123 (+/-) 0.0005592800434525817
Training Time:  3.1581902175114074 (+/-) 0.050302436396429756


=== Average network evolution ===
Total hidden node:  25.066666666666666 (+/-) 4.781445620544295


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=24, out_features=27, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 24
No. of nodes : 27
No. of parameters : 699

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=27, out_features=2, bias=True)
)
No. of inputs : 27
No. of output : 2
No. of parameters : 56
100% (30 of 30) |########################| Elapsed Time: 0:01:31 ETA:  00:00:00

=== Performance result ===
Accuracy:  80.54482758620689 (+/-) 2.255810307336873
Precision:  0.7847502637341663
Recall:  0.805448275862069
F1 score:  0.7670546648919138
Testing Time:  0.0023213912700784617 (+/-) 0.0004731759122633451
Training Time:  3.151699690983213 (+/-) 0.02857634124793602


=== Average network evolution ===
Total hidden node:  25.666666666666668 (+/-) 1.0434983894999017


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=24, out_features=26, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 24
No. of nodes : 26
No. of parameters : 674

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=26, out_features=2, bias=True)
)
No. of inputs : 26
No. of output : 2
No. of parameters : 54
100% (30 of 30) |########################| Elapsed Time: 0:01:31 ETA:  00:00:00

=== Performance result ===
Accuracy:  78.96206896551725 (+/-) 6.299612127802868
Precision:  0.7566961942964026
Recall:  0.7896206896551724
F1 score:  0.7535155260718467
Testing Time:  0.0024283425561312973 (+/-) 0.0006159721072666875
Training Time:  3.1666212739615607 (+/-) 0.07474227434558949


=== Average network evolution ===
Total hidden node:  24.966666666666665 (+/-) 4.771326393735346


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=24, out_features=27, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 24
No. of nodes : 27
No. of parameters : 699

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=27, out_features=2, bias=True)
)
No. of inputs : 27
No. of output : 2
No. of parameters : 56

========== Performance occupancy ==========
Preq Accuracy:  79.79 (+/-) 0.58
F1 score:  0.76 (+/-) 0.01
Precision:  0.77 (+/-) 0.01
Recall:  0.8 (+/-) 0.01
Training time:  3.15 (+/-) 0.01
Testing time:  0.0 (+/-) 0.0


========== Network ==========
Number of hidden layers:  1.0 (+/-) 0.0
Number of features:  22.4 (+/-) 6.86
50% Data
100% (30 of 30) |########################| Elapsed Time: 0:01:10 ETA:  00:00:00

=== Performance result ===
Accuracy:  80.20689655172414 (+/-) 2.520526906392824
Precision:  0.7795456061693482
Recall:  0.8020689655172414
F1 score:  0.7606792104779698
Testing Time:  0.0022929208032016098 (+/-) 0.00046592287797755645
Training Time:  2.4224132751596383 (+/-) 0.03953185063739474


=== Average network evolution ===
Total hidden node:  26.166666666666668 (+/-) 1.5293426329272615


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=24, out_features=28, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 24
No. of nodes : 28
No. of parameters : 724

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=28, out_features=2, bias=True)
)
No. of inputs : 28
No. of output : 2
No. of parameters : 58
100% (30 of 30) |########################| Elapsed Time: 0:01:09 ETA:  00:00:00

=== Performance result ===
Accuracy:  80.15172413793104 (+/-) 2.4471828546106065
Precision:  0.7789380637720327
Recall:  0.8015172413793104
F1 score:  0.7590956617645126
Testing Time:  0.0026160684125176793 (+/-) 0.0005378171657308437
Training Time:  2.401319273586931 (+/-) 0.030069161775021894


=== Average network evolution ===
Total hidden node:  25.366666666666667 (+/-) 0.7063206700139029


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=24, out_features=26, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 24
No. of nodes : 26
No. of parameters : 674

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=26, out_features=2, bias=True)
)
No. of inputs : 26
No. of output : 2
No. of parameters : 54
100% (30 of 30) |########################| Elapsed Time: 0:01:09 ETA:  00:00:00

=== Performance result ===
Accuracy:  77.73793103448274 (+/-) 9.88542688430292
Precision:  0.7446404420428647
Recall:  0.7773793103448275
F1 score:  0.750867424694555
Testing Time:  0.002423516635237069 (+/-) 0.0005578814949790215
Training Time:  2.404156240923651 (+/-) 0.019416307709653528


=== Average network evolution ===
Total hidden node:  33.666666666666664 (+/-) 1.5986105077709067


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=24, out_features=35, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 24
No. of nodes : 35
No. of parameters : 899

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=35, out_features=2, bias=True)
)
No. of inputs : 35
No. of output : 2
No. of parameters : 72
100% (30 of 30) |########################| Elapsed Time: 0:01:11 ETA:  00:00:00

=== Performance result ===
Accuracy:  78.37241379310343 (+/-) 6.441401461971805
Precision:  0.7503588333699214
Recall:  0.7837241379310345
F1 score:  0.7532750559943628
Testing Time:  0.0025039541310277478 (+/-) 0.0005661124779998831
Training Time:  2.4464977691913474 (+/-) 0.0789341616322422


=== Average network evolution ===
Total hidden node:  24.4 (+/-) 0.9865765724632497


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=24, out_features=25, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 24
No. of nodes : 25
No. of parameters : 649

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=25, out_features=2, bias=True)
)
No. of inputs : 25
No. of output : 2
No. of parameters : 52
100% (30 of 30) |########################| Elapsed Time: 0:01:10 ETA:  00:00:00

=== Performance result ===
Accuracy:  80.10000000000001 (+/-) 2.190575424324662
Precision:  0.7773100028022603
Recall:  0.801
F1 score:  0.7597471609441068
Testing Time:  0.0023942980273016566 (+/-) 0.0005584794959237563
Training Time:  2.4142231283516717 (+/-) 0.03093462727078375


=== Average network evolution ===
Total hidden node:  24.666666666666668 (+/-) 1.2995725793078614


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=24, out_features=26, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 24
No. of nodes : 26
No. of parameters : 674

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=26, out_features=2, bias=True)
)
No. of inputs : 26
No. of output : 2
No. of parameters : 54

========== Performance occupancy ==========
Preq Accuracy:  79.31 (+/-) 1.05
F1 score:  0.76 (+/-) 0.0
Precision:  0.77 (+/-) 0.02
Recall:  0.79 (+/-) 0.01
Training time:  2.42 (+/-) 0.02
Testing time:  0.0 (+/-) 0.0


========== Network ==========
Number of hidden layers:  1.0 (+/-) 0.0
Number of features:  28.0 (+/-) 3.63
25% Data
100% (30 of 30) |########################| Elapsed Time: 0:00:58 ETA:  00:00:00

=== Performance result ===
Accuracy:  77.17241379310344 (+/-) 7.595774530969636
Precision:  0.740289132036049
Recall:  0.7717241379310344
F1 score:  0.7482377080058107
Testing Time:  0.002598885832161739 (+/-) 0.0006693018373427925
Training Time:  2.029159373250501 (+/-) 0.014429045474099001


=== Average network evolution ===
Total hidden node:  30.633333333333333 (+/-) 1.3535960336164639


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=24, out_features=31, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 24
No. of nodes : 31
No. of parameters : 799

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=31, out_features=2, bias=True)
)
No. of inputs : 31
No. of output : 2
No. of parameters : 64
100% (30 of 30) |########################| Elapsed Time: 0:00:59 ETA:  00:00:00

=== Performance result ===
Accuracy:  77.54827586206896 (+/-) 7.823731391696506
Precision:  0.7406180403943232
Recall:  0.7754827586206896
F1 score:  0.7469928777515342
Testing Time:  0.002497500386731378 (+/-) 0.0005028338364391314
Training Time:  2.032955556080259 (+/-) 0.022217459568040734


=== Average network evolution ===
Total hidden node:  23.533333333333335 (+/-) 1.0241527663824812


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=24, out_features=25, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 24
No. of nodes : 25
No. of parameters : 649

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=25, out_features=2, bias=True)
)
No. of inputs : 25
No. of output : 2
No. of parameters : 52
100% (30 of 30) |########################| Elapsed Time: 0:00:59 ETA:  00:00:00

=== Performance result ===
Accuracy:  78.45862068965515 (+/-) 5.140207780677494
Precision:  0.7464460571405379
Recall:  0.7845862068965517
F1 score:  0.7424503830745596
Testing Time:  0.002570925087764345 (+/-) 0.0004913868311809277
Training Time:  2.036432693744528 (+/-) 0.02734745138627772


=== Average network evolution ===
Total hidden node:  21.133333333333333 (+/-) 1.4996295838935993


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=24, out_features=23, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 24
No. of nodes : 23
No. of parameters : 599

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=23, out_features=2, bias=True)
)
No. of inputs : 23
No. of output : 2
No. of parameters : 48
100% (30 of 30) |########################| Elapsed Time: 0:00:59 ETA:  00:00:00

=== Performance result ===
Accuracy:  76.55862068965517 (+/-) 11.413649337567335
Precision:  0.7236079411314116
Recall:  0.7655862068965518
F1 score:  0.7325835189173595
Testing Time:  0.002711345409524852 (+/-) 0.0007416231357634427
Training Time:  2.0496684600566994 (+/-) 0.04864396345403809


=== Average network evolution ===
Total hidden node:  39.03333333333333 (+/-) 5.896232318655325


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=24, out_features=41, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 24
No. of nodes : 41
No. of parameters : 1049

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=41, out_features=2, bias=True)
)
No. of inputs : 41
No. of output : 2
No. of parameters : 84
100% (30 of 30) |########################| Elapsed Time: 0:00:59 ETA:  00:00:00

=== Performance result ===
Accuracy:  76.39310344827587 (+/-) 7.611331436133744
Precision:  0.7298635229844239
Recall:  0.7639310344827587
F1 score:  0.7393716528395402
Testing Time:  0.0026394580972605736 (+/-) 0.000545270909923563
Training Time:  2.0439424103703994 (+/-) 0.036267434600251336


=== Average network evolution ===
Total hidden node:  29.366666666666667 (+/-) 4.1027091320519204


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=24, out_features=31, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 24
No. of nodes : 31
No. of parameters : 799

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=31, out_features=2, bias=True)
)
No. of inputs : 31
No. of output : 2
No. of parameters : 64
N/A% (0 of 30) |                         | Elapsed Time: 0:00:00 ETA:  --:--:--

========== Performance occupancy ==========
Preq Accuracy:  77.23 (+/-) 0.74
F1 score:  0.74 (+/-) 0.01
Precision:  0.74 (+/-) 0.01
Recall:  0.77 (+/-) 0.01
Training time:  2.04 (+/-) 0.01
Testing time:  0.0 (+/-) 0.0


========== Network ==========
Number of hidden layers:  1.0 (+/-) 0.0
Number of features:  30.2 (+/-) 6.27
Infinite Delay
100% (30 of 30) |########################| Elapsed Time: 0:00:51 ETA:  00:00:00

=== Performance result ===
Accuracy:  77.88620689655173 (+/-) 2.5099421806681654
Precision:  0.769578268282787
Recall:  0.7788620689655172
F1 score:  0.6826767469203531
Testing Time:  0.0031945869840424635 (+/-) 0.0007930072946805932
Training Time:  1.6654956916282917 (+/-) 0.02515726468773376


=== Average network evolution ===
Total hidden node:  16.733333333333334 (+/-) 16.733333333333334


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=24, out_features=19, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 24
No. of nodes : 19
No. of parameters : 499

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=19, out_features=2, bias=True)
)
No. of inputs : 19
No. of output : 2
No. of parameters : 40
100% (30 of 30) |########################| Elapsed Time: 0:00:51 ETA:  00:00:00

=== Performance result ===
Accuracy:  77.86551724137932 (+/-) 2.5064435392044997
Precision:  0.7538825779066591
Recall:  0.7786551724137931
F1 score:  0.6820554864008568
Testing Time:  0.002398359364476697 (+/-) 0.0005649736454469162
Training Time:  1.655294706081522 (+/-) 0.013172774831785014


=== Average network evolution ===
Total hidden node:  19.966666666666665 (+/-) 19.966666666666665


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=24, out_features=20, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 24
No. of nodes : 20
No. of parameters : 524

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=20, out_features=2, bias=True)
)
No. of inputs : 20
No. of output : 2
No. of parameters : 42
100% (30 of 30) |########################| Elapsed Time: 0:00:52 ETA:  00:00:00

=== Performance result ===
Accuracy:  24.075862068965524 (+/-) 10.494092103866029
Precision:  0.6563211379310345
Recall:  0.24075862068965517
F1 score:  0.13131070184378932
Testing Time:  0.003325503447960163 (+/-) 0.000653637931636334
Training Time:  1.6800545741771828 (+/-) 0.027289111519297093


=== Average network evolution ===
Total hidden node:  19.2 (+/-) 19.2


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=24, out_features=20, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 24
No. of nodes : 20
No. of parameters : 524

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=20, out_features=2, bias=True)
)
No. of inputs : 20
No. of output : 2
No. of parameters : 42
100% (30 of 30) |########################| Elapsed Time: 0:00:51 ETA:  00:00:00C:\Users\SCSE\AppData\Local\Continuum\miniconda3\envs\stmicro\lib\site-packages\sklearn\metrics\_classification.py:1221: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))

=== Performance result ===
Accuracy:  77.85517241379311 (+/-) 2.505247762115322
Precision:  0.6061427871581452
Recall:  0.7785517241379311
F1 score:  0.6816138984678044
Testing Time:  0.0025337400107548155 (+/-) 0.0005621418010552423
Training Time:  1.6651170089327056 (+/-) 0.017723554261637457


=== Average network evolution ===
Total hidden node:  21.3 (+/-) 21.3


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=24, out_features=22, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 24
No. of nodes : 22
No. of parameters : 574

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=22, out_features=2, bias=True)
)
No. of inputs : 22
No. of output : 2
No. of parameters : 46
100% (30 of 30) |########################| Elapsed Time: 0:00:52 ETA:  00:00:00

=== Performance result ===
Accuracy:  77.94827586206897 (+/-) 2.4547800926377215
Precision:  0.7587303163523433
Recall:  0.7794827586206896
F1 score:  0.6852941571748169
Testing Time:  0.0023812507760935814 (+/-) 0.0004770358391224454
Training Time:  1.6858411904039055 (+/-) 0.03339943032518744


=== Average network evolution ===
Total hidden node:  30.133333333333333 (+/-) 30.133333333333333


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=24, out_features=30, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 24
No. of nodes : 30
No. of parameters : 774

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=30, out_features=2, bias=True)
)
No. of inputs : 30
No. of output : 2
No. of parameters : 62

========== Performance occupancy ==========
Preq Accuracy:  67.13 (+/-) 21.53
F1 score:  0.57 (+/-) 0.22
Precision:  0.71 (+/-) 0.07
Recall:  0.67 (+/-) 0.22
Training time:  1.67 (+/-) 0.01
Testing time:  0.0 (+/-) 0.0


========== Network ==========
Number of hidden layers:  1.0 (+/-) 0.0
Number of features:  22.2 (+/-) 4.02
In [7]:
%run DEVDAN_electricitypricing.ipynb
Number of input:  8
Number of output:  2
Number of batch:  45
All Data
100% (45 of 45) |########################| Elapsed Time: 0:02:18 ETA:  00:00:00

=== Performance result ===
Accuracy:  69.11590909090908 (+/-) 7.438137082930295
Precision:  0.6878805969849514
Recall:  0.6911590909090909
F1 score:  0.6866115653008054
Testing Time:  0.001915552399375222 (+/-) 0.000444923711236873
Training Time:  3.1361293467608364 (+/-) 0.06438397107471447


=== Average network evolution ===
Total hidden node:  14.066666666666666 (+/-) 2.4073960113690385


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=16, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 16
No. of parameters : 152

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=16, out_features=2, bias=True)
)
No. of inputs : 16
No. of output : 2
No. of parameters : 34
100% (45 of 45) |########################| Elapsed Time: 0:02:19 ETA:  00:00:00

=== Performance result ===
Accuracy:  69.0340909090909 (+/-) 7.27101790991337
Precision:  0.687664634619826
Recall:  0.6903409090909091
F1 score:  0.688024974848844
Testing Time:  0.0020025480877269397 (+/-) 0.0005411429858569964
Training Time:  3.1674478433348914 (+/-) 0.09279921846311937


=== Average network evolution ===
Total hidden node:  14.822222222222223 (+/-) 0.8243216440440626


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=15, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 15
No. of parameters : 143

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=15, out_features=2, bias=True)
)
No. of inputs : 15
No. of output : 2
No. of parameters : 32
100% (45 of 45) |########################| Elapsed Time: 0:02:17 ETA:  00:00:00

=== Performance result ===
Accuracy:  69.36136363636363 (+/-) 7.098342185106287
Precision:  0.6920662772193343
Recall:  0.6936136363636364
F1 score:  0.6926035350075777
Testing Time:  0.0017343976280905983 (+/-) 0.0005686697325892421
Training Time:  3.1221403642134233 (+/-) 0.030190856528502532


=== Average network evolution ===
Total hidden node:  19.044444444444444 (+/-) 2.1077165691341113


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=22, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 22
No. of parameters : 206

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=22, out_features=2, bias=True)
)
No. of inputs : 22
No. of output : 2
No. of parameters : 46
100% (45 of 45) |########################| Elapsed Time: 0:02:18 ETA:  00:00:00

=== Performance result ===
Accuracy:  68.37272727272726 (+/-) 6.213342082543882
Precision:  0.680821048785843
Recall:  0.6837272727272727
F1 score:  0.6811806717059659
Testing Time:  0.0016485831954262474 (+/-) 0.00047600237412088916
Training Time:  3.133968087759885 (+/-) 0.04957929545266326


=== Average network evolution ===
Total hidden node:  9.0 (+/-) 1.3824294235551815


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=10, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 10
No. of parameters : 98

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=10, out_features=2, bias=True)
)
No. of inputs : 10
No. of output : 2
No. of parameters : 22
100% (45 of 45) |########################| Elapsed Time: 0:02:17 ETA:  00:00:00

=== Performance result ===
Accuracy:  68.13409090909092 (+/-) 7.3799773090873835
Precision:  0.6776965307277131
Recall:  0.681340909090909
F1 score:  0.6749474506960611
Testing Time:  0.0018241947347467596 (+/-) 0.0005223532411701956
Training Time:  3.1143344965848057 (+/-) 0.021943364230313307


=== Average network evolution ===
Total hidden node:  16.91111111111111 (+/-) 2.229321991819458


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=19, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 19
No. of parameters : 179

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=19, out_features=2, bias=True)
)
No. of inputs : 19
No. of output : 2
No. of parameters : 40

========== Performance occupancy ==========
Preq Accuracy:  68.8 (+/-) 0.47
F1 score:  0.68 (+/-) 0.01
Precision:  0.69 (+/-) 0.01
Recall:  0.69 (+/-) 0.0
Training time:  3.13 (+/-) 0.02
Testing time:  0.0 (+/-) 0.0


========== Network ==========
Number of hidden layers:  1.0 (+/-) 0.0
Number of features:  16.4 (+/-) 4.03
50% Data
100% (45 of 45) |########################| Elapsed Time: 0:01:44 ETA:  00:00:00

=== Performance result ===
Accuracy:  66.88636363636363 (+/-) 6.905320442472105
Precision:  0.6651406409466315
Recall:  0.6688636363636363
F1 score:  0.6586112862639065
Testing Time:  0.0017536607655611906 (+/-) 0.00041885168995711003
Training Time:  2.377365079793063 (+/-) 0.018819410110174538


=== Average network evolution ===
Total hidden node:  11.977777777777778 (+/-) 1.4218749576041236


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=13, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 13
No. of parameters : 125

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=13, out_features=2, bias=True)
)
No. of inputs : 13
No. of output : 2
No. of parameters : 28
100% (45 of 45) |########################| Elapsed Time: 0:01:45 ETA:  00:00:00

=== Performance result ===
Accuracy:  64.78636363636362 (+/-) 7.159564197919608
Precision:  0.6449983547479394
Recall:  0.6478636363636363
F1 score:  0.6458557794742396
Testing Time:  0.0018013607371937144 (+/-) 0.0004383535241080121
Training Time:  2.3839974891055715 (+/-) 0.03556945042333179


=== Average network evolution ===
Total hidden node:  8.71111111111111 (+/-) 0.6539528430916515


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=9, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 9
No. of parameters : 89

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=9, out_features=2, bias=True)
)
No. of inputs : 9
No. of output : 2
No. of parameters : 20
100% (45 of 45) |########################| Elapsed Time: 0:01:45 ETA:  00:00:00

=== Performance result ===
Accuracy:  67.31136363636364 (+/-) 5.878010482417071
Precision:  0.6690423295884627
Recall:  0.6731136363636364
F1 score:  0.6660395556676308
Testing Time:  0.001755280928178267 (+/-) 0.0005166947334056253
Training Time:  2.3952570936896582 (+/-) 0.04970239591934583


=== Average network evolution ===
Total hidden node:  11.688888888888888 (+/-) 1.2077936214845502


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=13, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 13
No. of parameters : 125

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=13, out_features=2, bias=True)
)
No. of inputs : 13
No. of output : 2
No. of parameters : 28
100% (45 of 45) |########################| Elapsed Time: 0:01:44 ETA:  00:00:00

=== Performance result ===
Accuracy:  66.26590909090908 (+/-) 5.985396743203722
Precision:  0.6582034714415427
Recall:  0.6626590909090909
F1 score:  0.6574849250712905
Testing Time:  0.001736527139490301 (+/-) 0.00048301170637693463
Training Time:  2.3815436471592295 (+/-) 0.02205901031729355


=== Average network evolution ===
Total hidden node:  10.466666666666667 (+/-) 1.32664991614216


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=11, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 11
No. of parameters : 107

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=11, out_features=2, bias=True)
)
No. of inputs : 11
No. of output : 2
No. of parameters : 24
100% (45 of 45) |########################| Elapsed Time: 0:01:45 ETA:  00:00:00

=== Performance result ===
Accuracy:  68.82954545454547 (+/-) 8.335836641913106
Precision:  0.6850497598357418
Recall:  0.6882954545454546
F1 score:  0.6820121868585988
Testing Time:  0.0018252134323120117 (+/-) 0.0005619156629883253
Training Time:  2.391730373555964 (+/-) 0.03150369469761112


=== Average network evolution ===
Total hidden node:  19.022222222222222 (+/-) 1.1448219442125562


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=20, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 20
No. of parameters : 188

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=20, out_features=2, bias=True)
)
No. of inputs : 20
No. of output : 2
No. of parameters : 42

========== Performance occupancy ==========
Preq Accuracy:  66.82 (+/-) 1.32
F1 score:  0.66 (+/-) 0.01
Precision:  0.66 (+/-) 0.01
Recall:  0.67 (+/-) 0.01
Training time:  2.39 (+/-) 0.01
Testing time:  0.0 (+/-) 0.0


========== Network ==========
Number of hidden layers:  1.0 (+/-) 0.0
Number of features:  13.2 (+/-) 3.71
25% Data
100% (45 of 45) |########################| Elapsed Time: 0:01:28 ETA:  00:00:00

=== Performance result ===
Accuracy:  65.95681818181818 (+/-) 7.775585266696612
Precision:  0.6573247624234327
Recall:  0.6595681818181818
F1 score:  0.6580740575833111
Testing Time:  0.0018908652392300692 (+/-) 0.00041587454585819274
Training Time:  2.007850105112249 (+/-) 0.014674920771549612


=== Average network evolution ===
Total hidden node:  16.977777777777778 (+/-) 2.4082163882922782


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=19, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 19
No. of parameters : 179

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=19, out_features=2, bias=True)
)
No. of inputs : 19
No. of output : 2
No. of parameters : 40
100% (45 of 45) |########################| Elapsed Time: 0:01:28 ETA:  00:00:00

=== Performance result ===
Accuracy:  64.25454545454544 (+/-) 6.09822830252788
Precision:  0.6363292137671945
Recall:  0.6425454545454545
F1 score:  0.6318161633015588
Testing Time:  0.0016665404493158514 (+/-) 0.0006259663902511844
Training Time:  2.0127531452612444 (+/-) 0.027050431766965182


=== Average network evolution ===
Total hidden node:  7.844444444444444 (+/-) 0.9650689222492651


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=9, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 9
No. of parameters : 89

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=9, out_features=2, bias=True)
)
No. of inputs : 9
No. of output : 2
No. of parameters : 20
100% (45 of 45) |########################| Elapsed Time: 0:01:28 ETA:  00:00:00

=== Performance result ===
Accuracy:  64.98636363636363 (+/-) 6.080729281512319
Precision:  0.6453805869807608
Recall:  0.6498636363636363
F1 score:  0.6456399956615226
Testing Time:  0.0019388253038579767 (+/-) 0.0005667536293338981
Training Time:  2.0177710869095544 (+/-) 0.023985740586651327


=== Average network evolution ===
Total hidden node:  13.466666666666667 (+/-) 1.0873004286866728


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=14, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 14
No. of parameters : 134

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=14, out_features=2, bias=True)
)
No. of inputs : 14
No. of output : 2
No. of parameters : 30
100% (45 of 45) |########################| Elapsed Time: 0:01:28 ETA:  00:00:00

=== Performance result ===
Accuracy:  64.35000000000001 (+/-) 5.597219277137857
Precision:  0.6400026079673325
Recall:  0.6435
F1 score:  0.6408670248425589
Testing Time:  0.0017346956513144753 (+/-) 0.0004837884511792188
Training Time:  2.014276921749115 (+/-) 0.021929229199596736


=== Average network evolution ===
Total hidden node:  15.444444444444445 (+/-) 2.206611837743361


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=17, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 17
No. of parameters : 161

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=17, out_features=2, bias=True)
)
No. of inputs : 17
No. of output : 2
No. of parameters : 36
100% (45 of 45) |########################| Elapsed Time: 0:01:28 ETA:  00:00:00

=== Performance result ===
Accuracy:  65.42045454545456 (+/-) 6.110519228996329
Precision:  0.6495921328977567
Recall:  0.6542045454545454
F1 score:  0.6494342384114868
Testing Time:  0.0017120133746754038 (+/-) 0.0004435141164211631
Training Time:  2.010752921754664 (+/-) 0.027896650958578715


=== Average network evolution ===
Total hidden node:  8.755555555555556 (+/-) 1.5798108966378863


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=10, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 10
No. of parameters : 98

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=10, out_features=2, bias=True)
)
No. of inputs : 10
No. of output : 2
No. of parameters : 22
N/A% (0 of 45) |                         | Elapsed Time: 0:00:00 ETA:  --:--:--

========== Performance occupancy ==========
Preq Accuracy:  64.99 (+/-) 0.64
F1 score:  0.65 (+/-) 0.01
Precision:  0.65 (+/-) 0.01
Recall:  0.65 (+/-) 0.01
Training time:  2.01 (+/-) 0.0
Testing time:  0.0 (+/-) 0.0


========== Network ==========
Number of hidden layers:  1.0 (+/-) 0.0
Number of features:  13.8 (+/-) 3.87
Infinite Delay
100% (45 of 45) |########################| Elapsed Time: 0:01:15 ETA:  00:00:00

=== Performance result ===
Accuracy:  57.98863636363637 (+/-) 7.074994889464615
Precision:  0.5570470421955053
Recall:  0.5798863636363636
F1 score:  0.5242768592447575
Testing Time:  0.0017226446758617055 (+/-) 0.0005381746399067189
Training Time:  1.6318173029206016 (+/-) 0.014913415487014097


=== Average network evolution ===
Total hidden node:  4.2 (+/-) 4.2


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=4, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 4
No. of parameters : 44

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=4, out_features=2, bias=True)
)
No. of inputs : 4
No. of output : 2
No. of parameters : 10
100% (45 of 45) |########################| Elapsed Time: 0:01:15 ETA:  00:00:00

=== Performance result ===
Accuracy:  55.78863636363636 (+/-) 5.5428174616546
Precision:  0.5231552622574426
Recall:  0.5578863636363637
F1 score:  0.504581935452061
Testing Time:  0.0016518831253051758 (+/-) 0.0005601404680834668
Training Time:  1.6447911587628452 (+/-) 0.01948767975843442


=== Average network evolution ===
Total hidden node:  6.177777777777778 (+/-) 6.177777777777778


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=6, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 6
No. of parameters : 62

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=6, out_features=2, bias=True)
)
No. of inputs : 6
No. of output : 2
No. of parameters : 14
100% (45 of 45) |########################| Elapsed Time: 0:01:16 ETA:  00:00:00

=== Performance result ===
Accuracy:  58.09090909090909 (+/-) 6.704605546726079
Precision:  0.5643252855732328
Recall:  0.5809090909090909
F1 score:  0.45989854777171846
Testing Time:  0.0016510865905068138 (+/-) 0.000562458128152547
Training Time:  1.656051830811934 (+/-) 0.014737095547373544


=== Average network evolution ===
Total hidden node:  7.622222222222222 (+/-) 7.622222222222222


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=7, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 7
No. of parameters : 71

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=7, out_features=2, bias=True)
)
No. of inputs : 7
No. of output : 2
No. of parameters : 16
100% (45 of 45) |########################| Elapsed Time: 0:01:15 ETA:  00:00:00

=== Performance result ===
Accuracy:  61.63409090909091 (+/-) 6.221916658138909
Precision:  0.612948157781875
Recall:  0.6163409090909091
F1 score:  0.5738345741524136
Testing Time:  0.001754441044547341 (+/-) 0.0006354518444211762
Training Time:  1.6443087458610535 (+/-) 0.018432656689547078


=== Average network evolution ===
Total hidden node:  13.955555555555556 (+/-) 13.955555555555556


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=14, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 14
No. of parameters : 134

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=14, out_features=2, bias=True)
)
No. of inputs : 14
No. of output : 2
No. of parameters : 30
100% (45 of 45) |########################| Elapsed Time: 0:01:18 ETA:  00:00:00

=== Performance result ===
Accuracy:  61.57272727272728 (+/-) 6.189704194590314
Precision:  0.6062952624377834
Recall:  0.6157272727272727
F1 score:  0.5987134434980798
Testing Time:  0.0017207915132695978 (+/-) 0.000495171145331022
Training Time:  1.7014540379697627 (+/-) 0.07965185737186324


=== Average network evolution ===
Total hidden node:  3.888888888888889 (+/-) 3.888888888888889


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=4, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 4
No. of parameters : 44

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=4, out_features=2, bias=True)
)
No. of inputs : 4
No. of output : 2
No. of parameters : 10

========== Performance occupancy ==========
Preq Accuracy:  59.02 (+/-) 2.27
F1 score:  0.53 (+/-) 0.05
Precision:  0.57 (+/-) 0.03
Recall:  0.59 (+/-) 0.02
Training time:  1.66 (+/-) 0.02
Testing time:  0.0 (+/-) 0.0


========== Network ==========
Number of hidden layers:  1.0 (+/-) 0.0
Number of features:  7.0 (+/-) 3.69
In [8]:
%run DEVDAN_rmnist.ipynb
Number of input:  784
Number of output:  10
Number of batch:  69
All Data
100% (69 of 69) |########################| Elapsed Time: 0:05:21 ETA:  00:00:00

=== Performance result ===
Accuracy:  91.20735294117647 (+/-) 4.281468830439008
Precision:  0.9121754367545558
Recall:  0.9120735294117647
F1 score:  0.912061606808019
Testing Time:  0.01707222531823551 (+/-) 0.0019145821885862737
Training Time:  4.7024281059994415 (+/-) 0.08675534703453633


=== Average network evolution ===
Total hidden node:  58.391304347826086 (+/-) 2.456682051970472


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=784, out_features=62, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 784
No. of nodes : 62
No. of parameters : 49454

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=62, out_features=10, bias=True)
)
No. of inputs : 62
No. of output : 10
No. of parameters : 630
100% (69 of 69) |########################| Elapsed Time: 0:05:19 ETA:  00:00:00

=== Performance result ===
Accuracy:  91.40588235294115 (+/-) 3.9306818130663967
Precision:  0.9140466919257819
Recall:  0.9140588235294118
F1 score:  0.9139909778905166
Testing Time:  0.01687918691074147 (+/-) 0.0026816331184010274
Training Time:  4.675958072437959 (+/-) 0.06743711113975903


=== Average network evolution ===
Total hidden node:  58.0 (+/-) 1.841549442134554


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=784, out_features=61, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 784
No. of nodes : 61
No. of parameters : 48669

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=61, out_features=10, bias=True)
)
No. of inputs : 61
No. of output : 10
No. of parameters : 620
100% (69 of 69) |########################| Elapsed Time: 0:05:20 ETA:  00:00:00

=== Performance result ===
Accuracy:  91.09264705882353 (+/-) 4.123544883330881
Precision:  0.9112019231697668
Recall:  0.9109264705882353
F1 score:  0.9109815804650563
Testing Time:  0.017588159617255714 (+/-) 0.003171387856496166
Training Time:  4.693253387423122 (+/-) 0.06415027373242652


=== Average network evolution ===
Total hidden node:  59.63768115942029 (+/-) 1.9409471353951546


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=784, out_features=60, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 784
No. of nodes : 60
No. of parameters : 47884

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=60, out_features=10, bias=True)
)
No. of inputs : 60
No. of output : 10
No. of parameters : 610
100% (69 of 69) |########################| Elapsed Time: 0:05:25 ETA:  00:00:00

=== Performance result ===
Accuracy:  91.00294117647057 (+/-) 4.596545076859207
Precision:  0.909878369100459
Recall:  0.9100294117647059
F1 score:  0.9099125104754633
Testing Time:  0.017782393623800838 (+/-) 0.00314970831055761
Training Time:  4.761308266836054 (+/-) 0.12095370393763206


=== Average network evolution ===
Total hidden node:  65.27536231884058 (+/-) 5.975515399445882


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=784, out_features=66, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 784
No. of nodes : 66
No. of parameters : 52594

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=66, out_features=10, bias=True)
)
No. of inputs : 66
No. of output : 10
No. of parameters : 670
100% (69 of 69) |########################| Elapsed Time: 0:05:19 ETA:  00:00:00

=== Performance result ===
Accuracy:  90.78676470588235 (+/-) 3.599587574895569
Precision:  0.9076948693931182
Recall:  0.9078676470588235
F1 score:  0.9077291183849773
Testing Time:  0.017133681213154513 (+/-) 0.0029130128240678083
Training Time:  4.676245226579554 (+/-) 0.11896093598016656


=== Average network evolution ===
Total hidden node:  53.91304347826087 (+/-) 0.44196958498483796


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=784, out_features=54, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 784
No. of nodes : 54
No. of parameters : 43174

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=54, out_features=10, bias=True)
)
No. of inputs : 54
No. of output : 10
No. of parameters : 550

========== Performance occupancy ==========
Preq Accuracy:  91.1 (+/-) 0.21
F1 score:  0.91 (+/-) 0.0
Precision:  0.91 (+/-) 0.0
Recall:  0.91 (+/-) 0.0
Training time:  4.7 (+/-) 0.03
Testing time:  0.02 (+/-) 0.0


========== Network ==========
Number of hidden layers:  1.0 (+/-) 0.0
Number of features:  60.6 (+/-) 3.88
50% Data
100% (69 of 69) |########################| Elapsed Time: 0:04:04 ETA:  00:00:00

=== Performance result ===
Accuracy:  89.48529411764704 (+/-) 4.54517406338151
Precision:  0.8946411095399074
Recall:  0.8948529411764706
F1 score:  0.8947092649512606
Testing Time:  0.017579155809739056 (+/-) 0.0035187127681345453
Training Time:  3.578778663102318 (+/-) 0.07623474988383902


=== Average network evolution ===
Total hidden node:  52.95652173913044 (+/-) 0.7505511522448727


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=784, out_features=54, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 784
No. of nodes : 54
No. of parameters : 43174

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=54, out_features=10, bias=True)
)
No. of inputs : 54
No. of output : 10
No. of parameters : 550
100% (69 of 69) |########################| Elapsed Time: 0:04:11 ETA:  00:00:00

=== Performance result ===
Accuracy:  88.83970588235294 (+/-) 5.733701702008264
Precision:  0.8890956008665238
Recall:  0.8883970588235294
F1 score:  0.8884828130318017
Testing Time:  0.018240879563724294 (+/-) 0.002735365512110943
Training Time:  3.6799114872427547 (+/-) 0.1631239712216963


=== Average network evolution ===
Total hidden node:  63.69565217391305 (+/-) 1.6794093839850406


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=784, out_features=64, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 784
No. of nodes : 64
No. of parameters : 51024

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=64, out_features=10, bias=True)
)
No. of inputs : 64
No. of output : 10
No. of parameters : 650
100% (69 of 69) |########################| Elapsed Time: 0:04:08 ETA:  00:00:00

=== Performance result ===
Accuracy:  88.00147058823529 (+/-) 6.045185071050563
Precision:  0.880101699909268
Recall:  0.880014705882353
F1 score:  0.8800184805569037
Testing Time:  0.017962894018958595 (+/-) 0.003170714975085655
Training Time:  3.6357354206197403 (+/-) 0.13321100776101344


=== Average network evolution ===
Total hidden node:  72.17391304347827 (+/-) 10.076456303910243


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=784, out_features=74, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 784
No. of nodes : 74
No. of parameters : 58874

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=74, out_features=10, bias=True)
)
No. of inputs : 74
No. of output : 10
No. of parameters : 750
100% (69 of 69) |########################| Elapsed Time: 0:04:03 ETA:  00:00:00

=== Performance result ===
Accuracy:  88.9779411764706 (+/-) 6.399720710547482
Precision:  0.8899817079802047
Recall:  0.8897794117647059
F1 score:  0.8896890426510843
Testing Time:  0.017855952767764822 (+/-) 0.003864937217027266
Training Time:  3.5657929918345284 (+/-) 0.08910307577283723


=== Average network evolution ===
Total hidden node:  53.05797101449275 (+/-) 1.8406367673456832


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=784, out_features=54, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 784
No. of nodes : 54
No. of parameters : 43174

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=54, out_features=10, bias=True)
)
No. of inputs : 54
No. of output : 10
No. of parameters : 550
100% (69 of 69) |########################| Elapsed Time: 0:04:06 ETA:  00:00:00

=== Performance result ===
Accuracy:  88.98235294117647 (+/-) 5.538287619633479
Precision:  0.889639125251107
Recall:  0.8898235294117647
F1 score:  0.8897070553381168
Testing Time:  0.017487049102783203 (+/-) 0.0023208450811236124
Training Time:  3.6025286316871643 (+/-) 0.0515585287315136


=== Average network evolution ===
Total hidden node:  60.84057971014493 (+/-) 0.926629992066422


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=784, out_features=61, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 784
No. of nodes : 61
No. of parameters : 48669

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=61, out_features=10, bias=True)
)
No. of inputs : 61
No. of output : 10
No. of parameters : 620

========== Performance occupancy ==========
Preq Accuracy:  88.86 (+/-) 0.48
F1 score:  0.89 (+/-) 0.0
Precision:  0.89 (+/-) 0.0
Recall:  0.89 (+/-) 0.0
Training time:  3.61 (+/-) 0.04
Testing time:  0.02 (+/-) 0.0


========== Network ==========
Number of hidden layers:  1.0 (+/-) 0.0
Number of features:  61.4 (+/-) 7.42
25% Data
100% (69 of 69) |########################| Elapsed Time: 0:03:29 ETA:  00:00:00

=== Performance result ===
Accuracy:  85.60294117647057 (+/-) 8.255568006756825
Precision:  0.8564512931821048
Recall:  0.8560294117647059
F1 score:  0.8560578097393996
Testing Time:  0.018413403454948876 (+/-) 0.003726084408041066
Training Time:  3.0616672424709095 (+/-) 0.0711913362567278


=== Average network evolution ===
Total hidden node:  56.2463768115942 (+/-) 0.907389903912958


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=784, out_features=56, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 784
No. of nodes : 56
No. of parameters : 44744

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=56, out_features=10, bias=True)
)
No. of inputs : 56
No. of output : 10
No. of parameters : 570
100% (69 of 69) |########################| Elapsed Time: 0:03:28 ETA:  00:00:00

=== Performance result ===
Accuracy:  86.3720588235294 (+/-) 6.8781804533961575
Precision:  0.8635549034718024
Recall:  0.8637205882352941
F1 score:  0.8635194394325155
Testing Time:  0.017909737194285673 (+/-) 0.003601132254286814
Training Time:  3.0407121391857372 (+/-) 0.05191835477606462


=== Average network evolution ===
Total hidden node:  54.94202898550725 (+/-) 0.4780412319556707


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=784, out_features=55, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 784
No. of nodes : 55
No. of parameters : 43959

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=55, out_features=10, bias=True)
)
No. of inputs : 55
No. of output : 10
No. of parameters : 560
100% (69 of 69) |########################| Elapsed Time: 0:03:31 ETA:  00:00:00

=== Performance result ===
Accuracy:  86.19558823529412 (+/-) 8.045448728456014
Precision:  0.8617422123635735
Recall:  0.8619558823529412
F1 score:  0.8616814522653437
Testing Time:  0.01930155824212467 (+/-) 0.003497060003830735
Training Time:  3.0850580404786503 (+/-) 0.16363298363406073


=== Average network evolution ===
Total hidden node:  78.71014492753623 (+/-) 7.5892781907936975


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=784, out_features=81, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 784
No. of nodes : 81
No. of parameters : 64369

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=81, out_features=10, bias=True)
)
No. of inputs : 81
No. of output : 10
No. of parameters : 820
100% (69 of 69) |########################| Elapsed Time: 0:03:25 ETA:  00:00:00

=== Performance result ===
Accuracy:  86.1029411764706 (+/-) 7.47424933449419
Precision:  0.8613072341758994
Recall:  0.8610294117647059
F1 score:  0.8610755767964675
Testing Time:  0.018737442353192496 (+/-) 0.0034206276362946032
Training Time:  3.0025552476153656 (+/-) 0.18770818497636385


=== Average network evolution ===
Total hidden node:  65.3913043478261 (+/-) 3.1031418921835616


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=784, out_features=66, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 784
No. of nodes : 66
No. of parameters : 52594

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=66, out_features=10, bias=True)
)
No. of inputs : 66
No. of output : 10
No. of parameters : 670
100% (69 of 69) |########################| Elapsed Time: 0:03:17 ETA:  00:00:00

=== Performance result ===
Accuracy:  86.6735294117647 (+/-) 6.996797957701769
Precision:  0.86660873487005
Recall:  0.866735294117647
F1 score:  0.8666113381236042
Testing Time:  0.018836785765255198 (+/-) 0.0034862526977909947
Training Time:  2.878607988357544 (+/-) 0.0963126107930057


=== Average network evolution ===
Total hidden node:  54.98550724637681 (+/-) 0.11951030798891768


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=784, out_features=55, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 784
No. of nodes : 55
No. of parameters : 43959

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=55, out_features=10, bias=True)
)
No. of inputs : 55
No. of output : 10
No. of parameters : 560
N/A% (0 of 69) |                         | Elapsed Time: 0:00:00 ETA:  --:--:--

========== Performance occupancy ==========
Preq Accuracy:  86.19 (+/-) 0.35
F1 score:  0.86 (+/-) 0.0
Precision:  0.86 (+/-) 0.0
Recall:  0.86 (+/-) 0.0
Training time:  3.01 (+/-) 0.07
Testing time:  0.02 (+/-) 0.0


========== Network ==========
Number of hidden layers:  1.0 (+/-) 0.0
Number of features:  62.6 (+/-) 10.09
Infinite Delay
100% (69 of 69) |########################| Elapsed Time: 0:02:53 ETA:  00:00:00

=== Performance result ===
Accuracy:  40.35147058823529 (+/-) 5.984796734644987
Precision:  0.5583164249563346
Recall:  0.40351470588235294
F1 score:  0.39279515775170626
Testing Time:  0.02642878714729758 (+/-) 0.0035416090104053
Training Time:  2.457667087807375 (+/-) 0.11507105679705569


=== Average network evolution ===
Total hidden node:  45.10144927536232 (+/-) 45.10144927536232


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=784, out_features=46, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 784
No. of nodes : 46
No. of parameters : 36894

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=46, out_features=10, bias=True)
)
No. of inputs : 46
No. of output : 10
No. of parameters : 470
100% (69 of 69) |########################| Elapsed Time: 0:02:33 ETA:  00:00:00

=== Performance result ===
Accuracy:  11.911764705882355 (+/-) 8.45301076560655
Precision:  0.6396257782256521
Recall:  0.11911764705882352
F1 score:  0.05044704152972008
Testing Time:  0.0464637419756721 (+/-) 0.010620419820038704
Training Time:  2.158467313822578 (+/-) 0.12781023236265102


=== Average network evolution ===
Total hidden node:  28.014492753623188 (+/-) 28.014492753623188


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=784, out_features=29, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 784
No. of nodes : 29
No. of parameters : 23549

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=29, out_features=10, bias=True)
)
No. of inputs : 29
No. of output : 10
No. of parameters : 300
100% (69 of 69) |########################| Elapsed Time: 0:03:00 ETA:  00:00:00

=== Performance result ===
Accuracy:  32.555882352941175 (+/-) 5.150396396878855
Precision:  0.5843715504291254
Recall:  0.3255588235294118
F1 score:  0.26665577384207656
Testing Time:  0.030684032860924217 (+/-) 0.003343341850675314
Training Time:  2.56908957046621 (+/-) 0.12418446109503803


=== Average network evolution ===
Total hidden node:  48.0 (+/-) 48.0


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=784, out_features=48, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 784
No. of nodes : 48
No. of parameters : 38464

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=48, out_features=10, bias=True)
)
No. of inputs : 48
No. of output : 10
No. of parameters : 490
100% (69 of 69) |########################| Elapsed Time: 0:03:03 ETA:  00:00:00

=== Performance result ===
Accuracy:  20.17941176470588 (+/-) 7.342614513187613
Precision:  0.629739736102647
Recall:  0.20179411764705882
F1 score:  0.1743979006296883
Testing Time:  0.03161644584992353 (+/-) 0.0033637960830123037
Training Time:  2.6099616920246795 (+/-) 0.11351286571923842


=== Average network evolution ===
Total hidden node:  48.88405797101449 (+/-) 48.88405797101449


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=784, out_features=49, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 784
No. of nodes : 49
No. of parameters : 39249

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=49, out_features=10, bias=True)
)
No. of inputs : 49
No. of output : 10
No. of parameters : 500
100% (69 of 69) |########################| Elapsed Time: 0:03:14 ETA:  00:00:00

=== Performance result ===
Accuracy:  20.755882352941175 (+/-) 7.301075310667706
Precision:  0.6021139882705219
Recall:  0.20755882352941177
F1 score:  0.0978856819264646
Testing Time:  0.042128647074979896 (+/-) 0.005231481572402563
Training Time:  2.755272826727699 (+/-) 0.12319388052125792


=== Average network evolution ===
Total hidden node:  49.17391304347826 (+/-) 49.17391304347826


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=784, out_features=49, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 784
No. of nodes : 49
No. of parameters : 39249

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=49, out_features=10, bias=True)
)
No. of inputs : 49
No. of output : 10
No. of parameters : 500

========== Performance occupancy ==========
Preq Accuracy:  25.15 (+/-) 10.05
F1 score:  0.2 (+/-) 0.12
Precision:  0.6 (+/-) 0.03
Recall:  0.25 (+/-) 0.1
Training time:  2.51 (+/-) 0.2
Testing time:  0.04 (+/-) 0.01


========== Network ==========
Number of hidden layers:  1.0 (+/-) 0.0
Number of features:  44.2 (+/-) 7.68
In [9]:
%run DEVDAN_pmnist.ipynb
Number of input:  784
Number of output:  10
Number of batch:  69
All Data
100% (69 of 69) |########################| Elapsed Time: 0:05:11 ETA:  00:00:00

=== Performance result ===
Accuracy:  84.46323529411768 (+/-) 14.220468930091421
Precision:  0.8477063888866383
Recall:  0.8446323529411764
F1 score:  0.8455863983439038
Testing Time:  0.019519462304956773 (+/-) 0.00653963938449298
Training Time:  4.56293657947989 (+/-) 0.20790287299562826


=== Average network evolution ===
Total hidden node:  66.84057971014492 (+/-) 2.872272182440777


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=784, out_features=68, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 784
No. of nodes : 68
No. of parameters : 54164

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=68, out_features=10, bias=True)
)
No. of inputs : 68
No. of output : 10
No. of parameters : 690
100% (69 of 69) |########################| Elapsed Time: 0:05:06 ETA:  00:00:00

=== Performance result ===
Accuracy:  83.64264705882354 (+/-) 15.483096249254146
Precision:  0.8372730319293231
Recall:  0.8364264705882353
F1 score:  0.8364451665917312
Testing Time:  0.019030735773198745 (+/-) 0.005757246363298547
Training Time:  4.480970561504364 (+/-) 0.15852254866187857


=== Average network evolution ===
Total hidden node:  67.42028985507247 (+/-) 3.047478392649437


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=784, out_features=68, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 784
No. of nodes : 68
No. of parameters : 54164

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=68, out_features=10, bias=True)
)
No. of inputs : 68
No. of output : 10
No. of parameters : 690
100% (69 of 69) |########################| Elapsed Time: 0:05:01 ETA:  00:00:00

=== Performance result ===
Accuracy:  83.73676470588235 (+/-) 15.780040486898825
Precision:  0.839320596369045
Recall:  0.8373676470588235
F1 score:  0.8378000633962865
Testing Time:  0.019588098806493422 (+/-) 0.006158839898437832
Training Time:  4.418669662054847 (+/-) 0.09511035752293326


=== Average network evolution ===
Total hidden node:  75.91304347826087 (+/-) 4.744910715046365


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=784, out_features=77, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 784
No. of nodes : 77
No. of parameters : 61229

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=77, out_features=10, bias=True)
)
No. of inputs : 77
No. of output : 10
No. of parameters : 780
100% (69 of 69) |########################| Elapsed Time: 0:05:31 ETA:  00:00:00

=== Performance result ===
Accuracy:  82.98970588235294 (+/-) 15.68634793947274
Precision:  0.8315275886908015
Recall:  0.8298970588235294
F1 score:  0.8300294273977369
Testing Time:  0.02139613207648782 (+/-) 0.009149734297194515
Training Time:  4.850568298031302 (+/-) 0.7032074593035993


=== Average network evolution ===
Total hidden node:  70.81159420289855 (+/-) 5.111156771756629


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=784, out_features=72, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 784
No. of nodes : 72
No. of parameters : 57304

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=72, out_features=10, bias=True)
)
No. of inputs : 72
No. of output : 10
No. of parameters : 730
100% (69 of 69) |########################| Elapsed Time: 0:06:00 ETA:  00:00:00

=== Performance result ===
Accuracy:  83.70294117647059 (+/-) 13.765344065145408
Precision:  0.8380800246294042
Recall:  0.8370294117647059
F1 score:  0.8368702258128398
Testing Time:  0.022298511336831486 (+/-) 0.008514839029296473
Training Time:  5.272772406830507 (+/-) 0.6826148103359203


=== Average network evolution ===
Total hidden node:  71.56521739130434 (+/-) 2.410594134892019


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=784, out_features=72, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 784
No. of nodes : 72
No. of parameters : 57304

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=72, out_features=10, bias=True)
)
No. of inputs : 72
No. of output : 10
No. of parameters : 730

========== Performance occupancy ==========
Preq Accuracy:  83.71 (+/-) 0.47
F1 score:  0.84 (+/-) 0.0
Precision:  0.84 (+/-) 0.01
Recall:  0.84 (+/-) 0.0
Training time:  4.72 (+/-) 0.31
Testing time:  0.02 (+/-) 0.0


========== Network ==========
Number of hidden layers:  1.0 (+/-) 0.0
Number of features:  71.4 (+/-) 3.32
50% Data
100% (69 of 69) |########################| Elapsed Time: 0:03:57 ETA:  00:00:00

=== Performance result ===
Accuracy:  80.64411764705882 (+/-) 16.311204939378158
Precision:  0.8088740858878152
Recall:  0.8064411764705882
F1 score:  0.8071685661665067
Testing Time:  0.019560855977675495 (+/-) 0.005556032377926591
Training Time:  3.4651774483568527 (+/-) 0.1155630773483468


=== Average network evolution ===
Total hidden node:  72.05797101449275 (+/-) 3.9485240609662506


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=784, out_features=73, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 784
No. of nodes : 73
No. of parameters : 58089

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=73, out_features=10, bias=True)
)
No. of inputs : 73
No. of output : 10
No. of parameters : 740
100% (69 of 69) |########################| Elapsed Time: 0:03:50 ETA:  00:00:00

=== Performance result ===
Accuracy:  79.90588235294116 (+/-) 15.704737786010172
Precision:  0.8007929928271266
Recall:  0.7990588235294117
F1 score:  0.799310424819239
Testing Time:  0.018970875179066378 (+/-) 0.005843724202964007
Training Time:  3.3753324571777794 (+/-) 0.18148726980565028


=== Average network evolution ===
Total hidden node:  58.44927536231884 (+/-) 2.8919490037200903


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=784, out_features=59, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 784
No. of nodes : 59
No. of parameters : 47099

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=59, out_features=10, bias=True)
)
No. of inputs : 59
No. of output : 10
No. of parameters : 600
100% (69 of 69) |########################| Elapsed Time: 0:03:53 ETA:  00:00:00

=== Performance result ===
Accuracy:  80.61617647058823 (+/-) 16.79972522791858
Precision:  0.8071697565957654
Recall:  0.8061617647058823
F1 score:  0.8063066282018548
Testing Time:  0.019190066000994516 (+/-) 0.00726453453979381
Training Time:  3.4093506897197052 (+/-) 0.16147735140998654


=== Average network evolution ===
Total hidden node:  67.15942028985508 (+/-) 3.697328406443708


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=784, out_features=68, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 784
No. of nodes : 68
No. of parameters : 54164

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=68, out_features=10, bias=True)
)
No. of inputs : 68
No. of output : 10
No. of parameters : 690
100% (69 of 69) |########################| Elapsed Time: 0:03:50 ETA:  00:00:00

=== Performance result ===
Accuracy:  81.42647058823529 (+/-) 15.070467981795106
Precision:  0.8179819748630814
Recall:  0.8142647058823529
F1 score:  0.8150378134510861
Testing Time:  0.01902237709830789 (+/-) 0.006990126299196121
Training Time:  3.3746082011391136 (+/-) 0.20019087998340945


=== Average network evolution ===
Total hidden node:  67.18840579710145 (+/-) 4.246995058124569


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=784, out_features=68, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 784
No. of nodes : 68
No. of parameters : 54164

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=68, out_features=10, bias=True)
)
No. of inputs : 68
No. of output : 10
No. of parameters : 690
100% (69 of 69) |########################| Elapsed Time: 0:03:49 ETA:  00:00:00

=== Performance result ===
Accuracy:  80.25441176470588 (+/-) 16.64575934181868
Precision:  0.8049818285180451
Recall:  0.8025441176470588
F1 score:  0.8033938721295196
Testing Time:  0.019356699550853056 (+/-) 0.00632902866724976
Training Time:  3.359912907376009 (+/-) 0.07699155493447761


=== Average network evolution ===
Total hidden node:  69.95652173913044 (+/-) 4.604455254593793


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=784, out_features=71, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 784
No. of nodes : 71
No. of parameters : 56519

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=71, out_features=10, bias=True)
)
No. of inputs : 71
No. of output : 10
No. of parameters : 720

========== Performance occupancy ==========
Preq Accuracy:  80.57 (+/-) 0.51
F1 score:  0.81 (+/-) 0.01
Precision:  0.81 (+/-) 0.01
Recall:  0.81 (+/-) 0.01
Training time:  3.4 (+/-) 0.04
Testing time:  0.02 (+/-) 0.0


========== Network ==========
Number of hidden layers:  1.0 (+/-) 0.0
Number of features:  67.8 (+/-) 4.79
25% Data
100% (69 of 69) |########################| Elapsed Time: 0:03:18 ETA:  00:00:00

=== Performance result ===
Accuracy:  76.26323529411764 (+/-) 18.35365730833219
Precision:  0.7632599069907098
Recall:  0.7626323529411765
F1 score:  0.7622666288465874
Testing Time:  0.020237466868232277 (+/-) 0.007883924198523126
Training Time:  2.892399111214806 (+/-) 0.07849819951815269


=== Average network evolution ===
Total hidden node:  75.34782608695652 (+/-) 3.020826679044449


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=784, out_features=76, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 784
No. of nodes : 76
No. of parameters : 60444

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=76, out_features=10, bias=True)
)
No. of inputs : 76
No. of output : 10
No. of parameters : 770
100% (69 of 69) |########################| Elapsed Time: 0:03:35 ETA:  00:00:00

=== Performance result ===
Accuracy:  76.75882352941177 (+/-) 17.991470489668785
Precision:  0.7719089970854155
Recall:  0.7675882352941177
F1 score:  0.7681206167185662
Testing Time:  0.020353804616367117 (+/-) 0.006372210879471908
Training Time:  3.14686339041766 (+/-) 0.1572943608352314


=== Average network evolution ===
Total hidden node:  105.57971014492753 (+/-) 16.192148568930026


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=784, out_features=109, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 784
No. of nodes : 109
No. of parameters : 86349

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=109, out_features=10, bias=True)
)
No. of inputs : 109
No. of output : 10
No. of parameters : 1100
100% (69 of 69) |########################| Elapsed Time: 0:03:36 ETA:  00:00:00

=== Performance result ===
Accuracy:  72.54705882352943 (+/-) 20.609017662094903
Precision:  0.7266106361396942
Recall:  0.7254705882352941
F1 score:  0.7258523036769005
Testing Time:  0.022645764491137338 (+/-) 0.008644239474507506
Training Time:  3.1532852509442497 (+/-) 0.32391587090899954


=== Average network evolution ===
Total hidden node:  108.52173913043478 (+/-) 28.071135670738194


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=784, out_features=118, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 784
No. of nodes : 118
No. of parameters : 93414

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=118, out_features=10, bias=True)
)
No. of inputs : 118
No. of output : 10
No. of parameters : 1190
100% (69 of 69) |########################| Elapsed Time: 0:03:20 ETA:  00:00:00

=== Performance result ===
Accuracy:  75.93529411764706 (+/-) 17.723611409193193
Precision:  0.7608392682886446
Recall:  0.7593529411764706
F1 score:  0.7594134027197383
Testing Time:  0.020824078251333797 (+/-) 0.007195452501504053
Training Time:  2.9196199459188126 (+/-) 0.09006584413496722


=== Average network evolution ===
Total hidden node:  76.01449275362319 (+/-) 3.661364098466811


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=784, out_features=77, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 784
No. of nodes : 77
No. of parameters : 61229

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=77, out_features=10, bias=True)
)
No. of inputs : 77
No. of output : 10
No. of parameters : 780
100% (69 of 69) |########################| Elapsed Time: 0:03:18 ETA:  00:00:00

=== Performance result ===
Accuracy:  76.74264705882354 (+/-) 18.30353000489628
Precision:  0.7718339088999195
Recall:  0.7674264705882353
F1 score:  0.7687114972534361
Testing Time:  0.020540973719428566 (+/-) 0.006068717508294874
Training Time:  2.9016337640145244 (+/-) 0.0864527580733426


=== Average network evolution ===
Total hidden node:  72.1159420289855 (+/-) 3.1325140705887433


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=784, out_features=73, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 784
No. of nodes : 73
No. of parameters : 58089

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=73, out_features=10, bias=True)
)
No. of inputs : 73
No. of output : 10
No. of parameters : 740
N/A% (0 of 69) |                         | Elapsed Time: 0:00:00 ETA:  --:--:--

========== Performance occupancy ==========
Preq Accuracy:  75.65 (+/-) 1.58
F1 score:  0.76 (+/-) 0.02
Precision:  0.76 (+/-) 0.02
Recall:  0.76 (+/-) 0.02
Training time:  3.0 (+/-) 0.12
Testing time:  0.02 (+/-) 0.0


========== Network ==========
Number of hidden layers:  1.0 (+/-) 0.0
Number of features:  90.6 (+/-) 18.96
Infinite Delay
100% (69 of 69) |########################| Elapsed Time: 0:03:10 ETA:  00:00:00

=== Performance result ===
Accuracy:  14.794117647058824 (+/-) 12.057288281037387
Precision:  0.4923295915143977
Recall:  0.14794117647058824
F1 score:  0.11077296634098843
Testing Time:  0.04539057787726907 (+/-) 0.009691218082167937
Training Time:  2.6980996552635643 (+/-) 0.10094805593908691


=== Average network evolution ===
Total hidden node:  48.666666666666664 (+/-) 48.666666666666664


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=784, out_features=49, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 784
No. of nodes : 49
No. of parameters : 39249

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=49, out_features=10, bias=True)
)
No. of inputs : 49
No. of output : 10
No. of parameters : 500
100% (69 of 69) |########################| Elapsed Time: 0:04:18 ETA:  00:00:00

=== Performance result ===
Accuracy:  13.144117647058824 (+/-) 5.901081215808755
Precision:  0.57568057093761
Recall:  0.13144117647058823
F1 score:  0.08903377247400275
Testing Time:  0.05407240811516257 (+/-) 0.01164466316740226
Training Time:  3.6930234327035794 (+/-) 0.15151468951744565


=== Average network evolution ===
Total hidden node:  39.0 (+/-) 39.0


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=784, out_features=39, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 784
No. of nodes : 39
No. of parameters : 31399

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=39, out_features=10, bias=True)
)
No. of inputs : 39
No. of output : 10
No. of parameters : 400
100% (69 of 69) |########################| Elapsed Time: 0:03:05 ETA:  00:00:00

=== Performance result ===
Accuracy:  12.735294117647058 (+/-) 3.3306404924526753
Precision:  0.5529513464004769
Recall:  0.12735294117647059
F1 score:  0.07498186872757526
Testing Time:  0.04363921810598934 (+/-) 0.007891193042713018
Training Time:  2.6308416689143463 (+/-) 0.10570466941161397


=== Average network evolution ===
Total hidden node:  45.98550724637681 (+/-) 45.98550724637681


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=784, out_features=46, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 784
No. of nodes : 46
No. of parameters : 36894

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=46, out_features=10, bias=True)
)
No. of inputs : 46
No. of output : 10
No. of parameters : 470
100% (69 of 69) |########################| Elapsed Time: 0:03:08 ETA:  00:00:00

=== Performance result ===
Accuracy:  16.966176470588238 (+/-) 12.592827210175193
Precision:  0.5568840085846568
Recall:  0.16966176470588235
F1 score:  0.15442680140180015
Testing Time:  0.04555094242095947 (+/-) 0.009359089565275739
Training Time:  2.6623107089715847 (+/-) 0.10166135441199978


=== Average network evolution ===
Total hidden node:  51.98550724637681 (+/-) 51.98550724637681


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=784, out_features=52, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 784
No. of nodes : 52
No. of parameters : 41604

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=52, out_features=10, bias=True)
)
No. of inputs : 52
No. of output : 10
No. of parameters : 530
100% (69 of 69) |########################| Elapsed Time: 0:03:09 ETA:  00:00:00

=== Performance result ===
Accuracy:  14.688235294117648 (+/-) 8.618559477897014
Precision:  0.5567975564179721
Recall:  0.14688235294117646
F1 score:  0.10612780652863711
Testing Time:  0.04555041649762322 (+/-) 0.0073884780938668
Training Time:  2.6771987711682037 (+/-) 0.10645972604388527


=== Average network evolution ===
Total hidden node:  53.98550724637681 (+/-) 53.98550724637681


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=784, out_features=54, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 784
No. of nodes : 54
No. of parameters : 43174

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=54, out_features=10, bias=True)
)
No. of inputs : 54
No. of output : 10
No. of parameters : 550

========== Performance occupancy ==========
Preq Accuracy:  14.47 (+/-) 1.49
F1 score:  0.11 (+/-) 0.03
Precision:  0.55 (+/-) 0.03
Recall:  0.14 (+/-) 0.01
Training time:  2.87 (+/-) 0.41
Testing time:  0.05 (+/-) 0.0


========== Network ==========
Number of hidden layers:  1.0 (+/-) 0.0
Number of features:  48.0 (+/-) 5.25
In [19]:
%run DEVDAN_hepmass.ipynb
Number of input:  28
Number of output:  2
Number of batch:  2000
All Data
100% (2000 of 2000) |####################| Elapsed Time: 1:31:46 ETA:  00:00:00

=== Performance result ===
Accuracy:  83.94497248624312 (+/-) 1.617551149919122
Precision:  0.840275600584852
Recall:  0.8394497248624312
F1 score:  0.8393514266670782
Testing Time:  0.002415422560752422 (+/-) 0.0005241059887008398
Training Time:  2.7385008901640915 (+/-) 0.05825420715262009


=== Average network evolution ===
Total hidden node:  14.9825 (+/-) 0.25533066795823794


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=28, out_features=15, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 28
No. of nodes : 15
No. of parameters : 463

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=15, out_features=2, bias=True)
)
No. of inputs : 15
No. of output : 2
No. of parameters : 32
100% (2000 of 2000) |####################| Elapsed Time: 1:31:49 ETA:  00:00:00

=== Performance result ===
Accuracy:  83.98689344672336 (+/-) 1.6790318275992033
Precision:  0.8406943545111044
Recall:  0.8398689344672337
F1 score:  0.8397710674470118
Testing Time:  0.0024690111617316837 (+/-) 0.0006760279173701602
Training Time:  2.740053920879431 (+/-) 0.056411695847366994


=== Average network evolution ===
Total hidden node:  16.9425 (+/-) 0.5110711789956465


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=28, out_features=17, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 28
No. of nodes : 17
No. of parameters : 521

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=17, out_features=2, bias=True)
)
No. of inputs : 17
No. of output : 2
No. of parameters : 36
100% (2000 of 2000) |####################| Elapsed Time: 1:31:52 ETA:  00:00:00

=== Performance result ===
Accuracy:  83.92516258129066 (+/-) 1.462884881721431
Precision:  0.8414218582324984
Recall:  0.8392516258129065
F1 score:  0.8389944414168139
Testing Time:  0.002476679199394314 (+/-) 0.0005371772400377058
Training Time:  2.741735331829695 (+/-) 0.04712511541327894


=== Average network evolution ===
Total hidden node:  21.9905 (+/-) 0.38263527019865823


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=28, out_features=22, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 28
No. of nodes : 22
No. of parameters : 666

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=22, out_features=2, bias=True)
)
No. of inputs : 22
No. of output : 2
No. of parameters : 46
100% (2000 of 2000) |####################| Elapsed Time: 1:32:03 ETA:  00:00:00

=== Performance result ===
Accuracy:  83.94917458729365 (+/-) 1.6823772661526757
Precision:  0.8408720748654416
Recall:  0.8394917458729365
F1 score:  0.8393280297896675
Testing Time:  0.002429525872479086 (+/-) 0.000524417335889239
Training Time:  2.7472197538378715 (+/-) 0.06656484856197609


=== Average network evolution ===
Total hidden node:  15.9275 (+/-) 0.5091598471992858


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=28, out_features=16, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 28
No. of nodes : 16
No. of parameters : 492

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=16, out_features=2, bias=True)
)
No. of inputs : 16
No. of output : 2
No. of parameters : 34
100% (2000 of 2000) |####################| Elapsed Time: 1:34:21 ETA:  00:00:00

=== Performance result ===
Accuracy:  84.05227613806903 (+/-) 1.6477199587056814
Precision:  0.8413378563985309
Recall:  0.8405227613806904
F1 score:  0.8404266905200606
Testing Time:  0.0024295195512261136 (+/-) 0.0005946276599019067
Training Time:  2.8159550720003024 (+/-) 0.28433889304271576


=== Average network evolution ===
Total hidden node:  10.8625 (+/-) 0.5259218097778413


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=28, out_features=11, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 28
No. of nodes : 11
No. of parameters : 347

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=11, out_features=2, bias=True)
)
No. of inputs : 11
No. of output : 2
No. of parameters : 24

========== Performance occupancy ==========
Preq Accuracy:  83.97 (+/-) 0.04
F1 score:  0.84 (+/-) 0.0
Precision:  0.84 (+/-) 0.0
Recall:  0.84 (+/-) 0.0
Training time:  2.76 (+/-) 0.03
Testing time:  0.0 (+/-) 0.0


========== Network ==========
Number of hidden layers:  1.0 (+/-) 0.0
Number of features:  16.2 (+/-) 3.54
50% Data
100% (2000 of 2000) |####################| Elapsed Time: 1:25:22 ETA:  00:00:00

=== Performance result ===
Accuracy:  83.20290145072536 (+/-) 1.5333679253167165
Precision:  0.8347911104092015
Recall:  0.8320290145072536
F1 score:  0.8316802463229234
Testing Time:  0.0027140078990682474 (+/-) 0.0006646677541460836
Training Time:  2.545525513034036 (+/-) 0.33814500561862465


=== Average network evolution ===
Total hidden node:  10.974 (+/-) 0.3454330615329111


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=28, out_features=11, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 28
No. of nodes : 11
No. of parameters : 347

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=11, out_features=2, bias=True)
)
No. of inputs : 11
No. of output : 2
No. of parameters : 24
100% (2000 of 2000) |####################| Elapsed Time: 1:20:43 ETA:  00:00:00

=== Performance result ===
Accuracy:  83.40575287643823 (+/-) 1.800889647569179
Precision:  0.8360561727896367
Recall:  0.8340575287643822
F1 score:  0.8338090908765071
Testing Time:  0.002615449308096736 (+/-) 0.0006026017746485783
Training Time:  2.4071752180630948 (+/-) 0.03408486555618928


=== Average network evolution ===
Total hidden node:  13.6075 (+/-) 0.7067133435842285


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=28, out_features=14, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 28
No. of nodes : 14
No. of parameters : 434

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=14, out_features=2, bias=True)
)
No. of inputs : 14
No. of output : 2
No. of parameters : 30
100% (2000 of 2000) |####################| Elapsed Time: 1:20:55 ETA:  00:00:00

=== Performance result ===
Accuracy:  83.47633816908454 (+/-) 1.6976561536149783
Precision:  0.8361477169766328
Recall:  0.8347633816908454
F1 score:  0.834591975112313
Testing Time:  0.002615268019332237 (+/-) 0.0005961787670204172
Training Time:  2.412870115372704 (+/-) 0.04198359680753023


=== Average network evolution ===
Total hidden node:  11.779 (+/-) 0.5675905214148664


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=28, out_features=12, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 28
No. of nodes : 12
No. of parameters : 376

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=12, out_features=2, bias=True)
)
No. of inputs : 12
No. of output : 2
No. of parameters : 26
100% (2000 of 2000) |####################| Elapsed Time: 1:21:10 ETA:  00:00:00

=== Performance result ===
Accuracy:  83.15852926463232 (+/-) 1.9373390718608576
Precision:  0.8341168659704457
Recall:  0.8315852926463232
F1 score:  0.8312641293250608
Testing Time:  0.002643382924982999 (+/-) 0.0006016567706170252
Training Time:  2.420537390668372 (+/-) 0.05151565320175395


=== Average network evolution ===
Total hidden node:  14.91 (+/-) 0.6526101439603894


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=28, out_features=15, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 28
No. of nodes : 15
No. of parameters : 463

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=15, out_features=2, bias=True)
)
No. of inputs : 15
No. of output : 2
No. of parameters : 32
100% (2000 of 2000) |####################| Elapsed Time: 1:20:49 ETA:  00:00:00

=== Performance result ===
Accuracy:  83.63126563281641 (+/-) 1.7679255440598047
Precision:  0.8376653272971607
Recall:  0.8363126563281641
F1 score:  0.836147479116078
Testing Time:  0.002614494679628938 (+/-) 0.0006374683777889488
Training Time:  2.410004387025895 (+/-) 0.037536546171158196


=== Average network evolution ===
Total hidden node:  11.983 (+/-) 0.20666639784928748


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=28, out_features=12, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 28
No. of nodes : 12
No. of parameters : 376

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=12, out_features=2, bias=True)
)
No. of inputs : 12
No. of output : 2
No. of parameters : 26

========== Performance occupancy ==========
Preq Accuracy:  83.37 (+/-) 0.18
F1 score:  0.83 (+/-) 0.0
Precision:  0.84 (+/-) 0.0
Recall:  0.83 (+/-) 0.0
Training time:  2.44 (+/-) 0.05
Testing time:  0.0 (+/-) 0.0


========== Network ==========
Number of hidden layers:  1.0 (+/-) 0.0
Number of features:  12.8 (+/-) 1.47
25% Data
100% (2000 of 2000) |####################| Elapsed Time: 1:08:27 ETA:  00:00:00

=== Performance result ===
Accuracy:  83.3791895947974 (+/-) 1.9568576313739636
Precision:  0.8345751674362907
Recall:  0.833791895947974
F1 score:  0.8336937175688032
Testing Time:  0.0026152254403263644 (+/-) 0.0008853610062663889
Training Time:  2.0390662587601405 (+/-) 0.036691067704053185


=== Average network evolution ===
Total hidden node:  15.6065 (+/-) 0.9506091468106121


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=28, out_features=16, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 28
No. of nodes : 16
No. of parameters : 492

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=16, out_features=2, bias=True)
)
No. of inputs : 16
No. of output : 2
No. of parameters : 34
100% (2000 of 2000) |####################| Elapsed Time: 1:04:19 ETA:  00:00:00

=== Performance result ===
Accuracy:  82.60200100050025 (+/-) 2.4684514628226246
Precision:  0.8284026274994908
Recall:  0.8260200100050025
F1 score:  0.8257022978311099
Testing Time:  0.0025530441097166017 (+/-) 0.0010492917626780643
Training Time:  1.9143049403272192 (+/-) 0.1176206457623524


=== Average network evolution ===
Total hidden node:  12.6615 (+/-) 0.9627656776183913


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=28, out_features=13, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 28
No. of nodes : 13
No. of parameters : 405

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=13, out_features=2, bias=True)
)
No. of inputs : 13
No. of output : 2
No. of parameters : 28
100% (2000 of 2000) |####################| Elapsed Time: 0:59:52 ETA:  00:00:00

=== Performance result ===
Accuracy:  83.0495247623812 (+/-) 2.2751344229700856
Precision:  0.8310488045006306
Recall:  0.8304952476238119
F1 score:  0.8304236271559869
Testing Time:  0.0025563472625671356 (+/-) 0.0005716842513456687
Training Time:  1.7811180863039322 (+/-) 0.05706431943391897


=== Average network evolution ===
Total hidden node:  13.73 (+/-) 0.9225508116087698


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=28, out_features=14, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 28
No. of nodes : 14
No. of parameters : 434

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=14, out_features=2, bias=True)
)
No. of inputs : 14
No. of output : 2
No. of parameters : 30
100% (2000 of 2000) |####################| Elapsed Time: 1:00:12 ETA:  00:00:00

=== Performance result ===
Accuracy:  83.17868934467234 (+/-) 2.2626944062399446
Precision:  0.8326866153493208
Recall:  0.8317868934467234
F1 score:  0.8316721655407643
Testing Time:  0.002417790883776544 (+/-) 0.0005446077076096997
Training Time:  1.7914270170334878 (+/-) 0.0720721146030465


=== Average network evolution ===
Total hidden node:  15.823 (+/-) 0.9201472708213616


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=28, out_features=16, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 28
No. of nodes : 16
No. of parameters : 492

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=16, out_features=2, bias=True)
)
No. of inputs : 16
No. of output : 2
No. of parameters : 34
100% (2000 of 2000) |####################| Elapsed Time: 0:59:38 ETA:  00:00:00

=== Performance result ===
Accuracy:  82.56288144072036 (+/-) 1.8273457520949818
Precision:  0.8279498074644591
Recall:  0.8256288144072036
F1 score:  0.8253181887021902
Testing Time:  0.002401047196610085 (+/-) 0.0005454930307811034
Training Time:  1.7742607118846059 (+/-) 0.03826508549160752


=== Average network evolution ===
Total hidden node:  10.455 (+/-) 0.6949640278460462


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=28, out_features=11, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 28
No. of nodes : 11
No. of parameters : 347

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=11, out_features=2, bias=True)
)
No. of inputs : 11
No. of output : 2
No. of parameters : 24
N/A% (0 of 2000) |                       | Elapsed Time: 0:00:00 ETA:  --:--:--

========== Performance occupancy ==========
Preq Accuracy:  82.95 (+/-) 0.32
F1 score:  0.83 (+/-) 0.0
Precision:  0.83 (+/-) 0.0
Recall:  0.83 (+/-) 0.0
Training time:  1.86 (+/-) 0.1
Testing time:  0.0 (+/-) 0.0


========== Network ==========
Number of hidden layers:  1.0 (+/-) 0.0
Number of features:  14.0 (+/-) 1.9
Infinite Delay
100% (2000 of 2000) |####################| Elapsed Time: 0:48:35 ETA:  00:00:00

=== Performance result ===
Accuracy:  50.75472736368184 (+/-) 2.157684920305618
Precision:  0.5087542212437823
Recall:  0.5075472736368184
F1 score:  0.49043963303755456
Testing Time:  0.0023691895128548773 (+/-) 0.0005888000906879686
Training Time:  1.4410137990643348 (+/-) 0.02794844091858741


=== Average network evolution ===
Total hidden node:  4.973 (+/-) 4.973


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=28, out_features=4, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 28
No. of nodes : 4
No. of parameters : 144

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=4, out_features=2, bias=True)
)
No. of inputs : 4
No. of output : 2
No. of parameters : 10
100% (2000 of 2000) |####################| Elapsed Time: 0:48:47 ETA:  00:00:00

=== Performance result ===
Accuracy:  53.42706353176588 (+/-) 2.9209191731154887
Precision:  0.5383581662827182
Recall:  0.5342706353176588
F1 score:  0.5216177333439694
Testing Time:  0.0023720186910013846 (+/-) 0.0006796684575414441
Training Time:  1.4470708457275054 (+/-) 0.030957027793999028


=== Average network evolution ===
Total hidden node:  5.7255 (+/-) 5.7255


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=28, out_features=5, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 28
No. of nodes : 5
No. of parameters : 173

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=5, out_features=2, bias=True)
)
No. of inputs : 5
No. of output : 2
No. of parameters : 12
100% (2000 of 2000) |####################| Elapsed Time: 0:48:45 ETA:  00:00:00

=== Performance result ===
Accuracy:  51.96468234117058 (+/-) 3.7916159434170686
Precision:  0.5616023806753287
Recall:  0.5196468234117059
F1 score:  0.42086200549438646
Testing Time:  0.002382431702950169 (+/-) 0.0005195655447862198
Training Time:  1.4461388783552696 (+/-) 0.03516382186684283


=== Average network evolution ===
Total hidden node:  3.97 (+/-) 3.97


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=28, out_features=4, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 28
No. of nodes : 4
No. of parameters : 144

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=4, out_features=2, bias=True)
)
No. of inputs : 4
No. of output : 2
No. of parameters : 10
100% (2000 of 2000) |####################| Elapsed Time: 0:48:57 ETA:  00:00:00

=== Performance result ===
Accuracy:  51.49979989994998 (+/-) 2.401321122121272
Precision:  0.5163623994323763
Recall:  0.5149979989994997
F1 score:  0.5044768976762106
Testing Time:  0.0023855894669823313 (+/-) 0.0005291492071272844
Training Time:  1.4524227999161934 (+/-) 0.029726907650753864


=== Average network evolution ===
Total hidden node:  11.9735 (+/-) 11.9735


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=28, out_features=12, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 28
No. of nodes : 12
No. of parameters : 376

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=12, out_features=2, bias=True)
)
No. of inputs : 12
No. of output : 2
No. of parameters : 26
100% (2000 of 2000) |####################| Elapsed Time: 0:49:04 ETA:  00:00:00

=== Performance result ===
Accuracy:  52.803251625812905 (+/-) 3.4481892983034697
Precision:  0.529688862025156
Recall:  0.5280325162581291
F1 score:  0.5214419466575607
Testing Time:  0.0023869110859293173 (+/-) 0.0005301014485385265
Training Time:  1.4558078914716759 (+/-) 0.03763215248394666


=== Average network evolution ===
Total hidden node:  4.0665 (+/-) 4.0665


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=28, out_features=4, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 28
No. of nodes : 4
No. of parameters : 144

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=4, out_features=2, bias=True)
)
No. of inputs : 4
No. of output : 2
No. of parameters : 10

========== Performance occupancy ==========
Preq Accuracy:  52.09 (+/-) 0.94
F1 score:  0.49 (+/-) 0.04
Precision:  0.53 (+/-) 0.02
Recall:  0.52 (+/-) 0.01
Training time:  1.45 (+/-) 0.01
Testing time:  0.0 (+/-) 0.0


========== Network ==========
Number of hidden layers:  1.0 (+/-) 0.0
Number of features:  5.8 (+/-) 3.12
In [20]:
%run DEVDAN_susy.ipynb
Number of input:  18
Number of output:  2
Number of batch:  2000
All Data
100% (2000 of 2000) |####################| Elapsed Time: 1:31:29 ETA:  00:00:00

=== Performance result ===
Accuracy:  76.97398699349675 (+/-) 2.717476034821803
Precision:  0.7735739685058987
Recall:  0.7697398699349675
F1 score:  0.7666964423079438
Testing Time:  0.002090639922546112 (+/-) 0.00047567050193025374
Training Time:  2.7306137197073728 (+/-) 0.05769203579874548


=== Average network evolution ===
Total hidden node:  11.838 (+/-) 2.8081588274169964


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=18, out_features=17, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 18
No. of nodes : 17
No. of parameters : 341

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=17, out_features=2, bias=True)
)
No. of inputs : 17
No. of output : 2
No. of parameters : 36
100% (2000 of 2000) |####################| Elapsed Time: 1:31:38 ETA:  00:00:00

=== Performance result ===
Accuracy:  76.98519259629816 (+/-) 2.8082118647573395
Precision:  0.7734010443215474
Recall:  0.7698519259629815
F1 score:  0.7669291806356665
Testing Time:  0.002060988713885141 (+/-) 0.0004845275830802349
Training Time:  2.735074549928315 (+/-) 0.060216675398504636


=== Average network evolution ===
Total hidden node:  14.298 (+/-) 1.1925585939483225


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=18, out_features=16, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 18
No. of nodes : 16
No. of parameters : 322

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=16, out_features=2, bias=True)
)
No. of inputs : 16
No. of output : 2
No. of parameters : 34
100% (2000 of 2000) |####################| Elapsed Time: 1:31:46 ETA:  00:00:00

=== Performance result ===
Accuracy:  77.48504252126062 (+/-) 2.4199771756068436
Precision:  0.777128413816308
Recall:  0.7748504252126063
F1 score:  0.7726037654440399
Testing Time:  0.0021290051573333055 (+/-) 0.0004895105390619302
Training Time:  2.7388323221640802 (+/-) 0.06267061563097323


=== Average network evolution ===
Total hidden node:  23.338 (+/-) 3.565915871133249


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=18, out_features=27, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 18
No. of nodes : 27
No. of parameters : 531

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=27, out_features=2, bias=True)
)
No. of inputs : 27
No. of output : 2
No. of parameters : 56
100% (2000 of 2000) |####################| Elapsed Time: 1:47:16 ETA:  00:00:00

=== Performance result ===
Accuracy:  77.35272636318159 (+/-) 2.6901505116903968
Precision:  0.7752844998478545
Recall:  0.7735272636318159
F1 score:  0.7714931359734093
Testing Time:  0.0024418880964530115 (+/-) 0.0012863634862076206
Training Time:  3.202883983266658 (+/-) 0.363274596971193


=== Average network evolution ===
Total hidden node:  23.5815 (+/-) 3.8351476829452085


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=18, out_features=27, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 18
No. of nodes : 27
No. of parameters : 531

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=27, out_features=2, bias=True)
)
No. of inputs : 27
No. of output : 2
No. of parameters : 56
100% (2000 of 2000) |####################| Elapsed Time: 1:59:12 ETA:  00:00:00

=== Performance result ===
Accuracy:  77.4376188094047 (+/-) 2.5450902292264286
Precision:  0.7758681854082652
Recall:  0.7743761880940471
F1 score:  0.772490368800658
Testing Time:  0.002634201841750343 (+/-) 0.0011834921047449844
Training Time:  3.560552574623341 (+/-) 0.4193703165050777


=== Average network evolution ===
Total hidden node:  21.0775 (+/-) 3.712343431041907


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=18, out_features=24, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 18
No. of nodes : 24
No. of parameters : 474

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=24, out_features=2, bias=True)
)
No. of inputs : 24
No. of output : 2
No. of parameters : 50

========== Performance occupancy ==========
Preq Accuracy:  77.25 (+/-) 0.22
F1 score:  0.77 (+/-) 0.0
Precision:  0.78 (+/-) 0.0
Recall:  0.77 (+/-) 0.0
Training time:  2.99 (+/-) 0.34
Testing time:  0.0 (+/-) 0.0


========== Network ==========
Number of hidden layers:  1.0 (+/-) 0.0
Number of features:  22.2 (+/-) 4.79
50% Data
100% (2000 of 2000) |####################| Elapsed Time: 1:23:51 ETA:  00:00:00

=== Performance result ===
Accuracy:  76.7576288144072 (+/-) 2.955108612851145
Precision:  0.7697308580460802
Recall:  0.7675762881440721
F1 score:  0.7652135475961187
Testing Time:  0.002299461083271433 (+/-) 0.0005664678502657382
Training Time:  2.501218373564376 (+/-) 0.05753238442573188


=== Average network evolution ===
Total hidden node:  14.7215 (+/-) 2.4188711726753866


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=18, out_features=18, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 18
No. of nodes : 18
No. of parameters : 360

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=18, out_features=2, bias=True)
)
No. of inputs : 18
No. of output : 2
No. of parameters : 38
100% (2000 of 2000) |####################| Elapsed Time: 1:23:41 ETA:  00:00:00

=== Performance result ===
Accuracy:  76.83806903451726 (+/-) 3.0423287717494185
Precision:  0.7699622027183309
Recall:  0.7683806903451725
F1 score:  0.7663218990684774
Testing Time:  0.002301635713562958 (+/-) 0.0005765694894401364
Training Time:  2.4960943728223213 (+/-) 0.050810992016208575


=== Average network evolution ===
Total hidden node:  19.9865 (+/-) 4.16236924719564


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=18, out_features=25, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 18
No. of nodes : 25
No. of parameters : 493

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=25, out_features=2, bias=True)
)
No. of inputs : 25
No. of output : 2
No. of parameters : 52
100% (2000 of 2000) |####################| Elapsed Time: 1:23:24 ETA:  00:00:00

=== Performance result ===
Accuracy:  76.8687843921961 (+/-) 2.891431524550962
Precision:  0.7700361331116216
Recall:  0.768687843921961
F1 score:  0.7667584671569725
Testing Time:  0.002316659065769457 (+/-) 0.001073298156615216
Training Time:  2.4877691871228964 (+/-) 0.05020084951208561


=== Average network evolution ===
Total hidden node:  18.2715 (+/-) 4.753923405987942


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=18, out_features=23, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 18
No. of nodes : 23
No. of parameters : 455

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=23, out_features=2, bias=True)
)
No. of inputs : 23
No. of output : 2
No. of parameters : 48
100% (2000 of 2000) |####################| Elapsed Time: 1:22:43 ETA:  00:00:00

=== Performance result ===
Accuracy:  77.01610805402701 (+/-) 2.6885227798363576
Precision:  0.7722616957989414
Recall:  0.7701610805402701
F1 score:  0.7678864605916301
Testing Time:  0.0022730450441743088 (+/-) 0.0005915107902712769
Training Time:  2.467009422718256 (+/-) 0.05937490229458213


=== Average network evolution ===
Total hidden node:  18.6385 (+/-) 1.962604837964077


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=18, out_features=21, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 18
No. of nodes : 21
No. of parameters : 417

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=21, out_features=2, bias=True)
)
No. of inputs : 21
No. of output : 2
No. of parameters : 44
100% (2000 of 2000) |####################| Elapsed Time: 1:23:22 ETA:  00:00:00

=== Performance result ===
Accuracy:  76.6591795897949 (+/-) 2.8653637957691664
Precision:  0.7684092597619984
Recall:  0.766591795897949
F1 score:  0.7643715158640759
Testing Time:  0.0022854710770225813 (+/-) 0.0012547480099249176
Training Time:  2.4861639875838493 (+/-) 0.11608222738610692


=== Average network evolution ===
Total hidden node:  14.923 (+/-) 1.9738467519035008


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=18, out_features=17, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 18
No. of nodes : 17
No. of parameters : 341

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=17, out_features=2, bias=True)
)
No. of inputs : 17
No. of output : 2
No. of parameters : 36

========== Performance occupancy ==========
Preq Accuracy:  76.83 (+/-) 0.12
F1 score:  0.77 (+/-) 0.0
Precision:  0.77 (+/-) 0.0
Recall:  0.77 (+/-) 0.0
Training time:  2.49 (+/-) 0.01
Testing time:  0.0 (+/-) 0.0


========== Network ==========
Number of hidden layers:  1.0 (+/-) 0.0
Number of features:  20.8 (+/-) 2.99
25% Data
100% (2000 of 2000) |####################| Elapsed Time: 1:03:02 ETA:  00:00:00

=== Performance result ===
Accuracy:  75.77238619309655 (+/-) 3.7100471808282234
Precision:  0.7590134389026876
Recall:  0.7577238619309655
F1 score:  0.7555809434129982
Testing Time:  0.0022550687126781776 (+/-) 0.0028760468676830935
Training Time:  1.8771466827201748 (+/-) 0.23298772328929407


=== Average network evolution ===
Total hidden node:  12.518 (+/-) 2.170639537095001


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=18, out_features=15, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 18
No. of nodes : 15
No. of parameters : 303

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=15, out_features=2, bias=True)
)
No. of inputs : 15
No. of output : 2
No. of parameters : 32
100% (2000 of 2000) |####################| Elapsed Time: 0:59:05 ETA:  00:00:00

=== Performance result ===
Accuracy:  75.79779889944973 (+/-) 3.7585780039643626
Precision:  0.7597817297730193
Recall:  0.7579779889944972
F1 score:  0.7555517265816827
Testing Time:  0.002085630747006499 (+/-) 0.0007181364372320873
Training Time:  1.7592337274622953 (+/-) 0.15554612589621944


=== Average network evolution ===
Total hidden node:  15.2445 (+/-) 4.657544390556037


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=18, out_features=22, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 18
No. of nodes : 22
No. of parameters : 436

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=22, out_features=2, bias=True)
)
No. of inputs : 22
No. of output : 2
No. of parameters : 46
100% (2000 of 2000) |####################| Elapsed Time: 0:56:38 ETA:  00:00:00

=== Performance result ===
Accuracy:  76.02711355677839 (+/-) 3.3185285200492847
Precision:  0.7618248566557027
Recall:  0.7602711355677839
F1 score:  0.7580390682321614
Testing Time:  0.002108743394715241 (+/-) 0.00045909816414511993
Training Time:  1.6863909511938282 (+/-) 0.03688547261906658


=== Average network evolution ===
Total hidden node:  18.4645 (+/-) 4.655291585926708


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=18, out_features=24, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 18
No. of nodes : 24
No. of parameters : 474

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=24, out_features=2, bias=True)
)
No. of inputs : 24
No. of output : 2
No. of parameters : 50
100% (2000 of 2000) |####################| Elapsed Time: 0:56:30 ETA:  00:00:00

=== Performance result ===
Accuracy:  75.65167583791896 (+/-) 3.6694847734011105
Precision:  0.7592734028028071
Recall:  0.7565167583791896
F1 score:  0.7535592229279618
Testing Time:  0.002000094533503324 (+/-) 0.00048576565723468896
Training Time:  1.6820502683125238 (+/-) 0.03796032489101617


=== Average network evolution ===
Total hidden node:  12.18 (+/-) 2.3953287874527787


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=18, out_features=16, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 18
No. of nodes : 16
No. of parameters : 322

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=16, out_features=2, bias=True)
)
No. of inputs : 16
No. of output : 2
No. of parameters : 34
100% (2000 of 2000) |####################| Elapsed Time: 0:56:48 ETA:  00:00:00

=== Performance result ===
Accuracy:  75.97173586793397 (+/-) 3.5715395119628583
Precision:  0.7614283004033627
Recall:  0.7597173586793396
F1 score:  0.7573857215221373
Testing Time:  0.002102606889305859 (+/-) 0.000496291871148963
Training Time:  1.6910256031097444 (+/-) 0.040681664005599846


=== Average network evolution ===
Total hidden node:  19.8635 (+/-) 2.710695067690204


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=18, out_features=24, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 18
No. of nodes : 24
No. of parameters : 474

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=24, out_features=2, bias=True)
)
No. of inputs : 24
No. of output : 2
No. of parameters : 50
N/A% (0 of 2000) |                       | Elapsed Time: 0:00:00 ETA:  --:--:--

========== Performance occupancy ==========
Preq Accuracy:  75.84 (+/-) 0.14
F1 score:  0.76 (+/-) 0.0
Precision:  0.76 (+/-) 0.0
Recall:  0.76 (+/-) 0.0
Training time:  1.74 (+/-) 0.07
Testing time:  0.0 (+/-) 0.0


========== Network ==========
Number of hidden layers:  1.0 (+/-) 0.0
Number of features:  20.2 (+/-) 3.92
Infinite Delay
100% (2000 of 2000) |####################| Elapsed Time: 0:46:12 ETA:  00:00:00

=== Performance result ===
Accuracy:  45.906403201600796 (+/-) 1.9756924608500392
Precision:  0.4997991165105068
Recall:  0.459064032016008
F1 score:  0.3064849628778757
Testing Time:  0.001980981807699199 (+/-) 0.00045426592244336174
Training Time:  1.371322394132972 (+/-) 0.02922666062749222


=== Average network evolution ===
Total hidden node:  4.978 (+/-) 4.978


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=18, out_features=5, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 18
No. of nodes : 5
No. of parameters : 113

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=5, out_features=2, bias=True)
)
No. of inputs : 5
No. of output : 2
No. of parameters : 12
100% (2000 of 2000) |####################| Elapsed Time: 0:46:24 ETA:  00:00:00

=== Performance result ===
Accuracy:  54.50350175087544 (+/-) 1.5744164434610863
Precision:  0.5519056696032544
Recall:  0.5450350175087544
F1 score:  0.4035039520778062
Testing Time:  0.001995535359614011 (+/-) 0.00045898116057726114
Training Time:  1.3772968506443315 (+/-) 0.03396331840364975


=== Average network evolution ===
Total hidden node:  7.023 (+/-) 7.023


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=18, out_features=7, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 18
No. of nodes : 7
No. of parameters : 151

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=7, out_features=2, bias=True)
)
No. of inputs : 7
No. of output : 2
No. of parameters : 16
100% (2000 of 2000) |####################| Elapsed Time: 0:46:57 ETA:  00:00:00

=== Performance result ===
Accuracy:  55.794447223611805 (+/-) 1.7546776424476087
Precision:  0.6309272672752251
Recall:  0.5579444722361181
F1 score:  0.4300309636989829
Testing Time:  0.0020052767682516796 (+/-) 0.00046534598983510086
Training Time:  1.393513302137519 (+/-) 0.06203093630588441


=== Average network evolution ===
Total hidden node:  14.996 (+/-) 14.996


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=18, out_features=15, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 18
No. of nodes : 15
No. of parameters : 303

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=15, out_features=2, bias=True)
)
No. of inputs : 15
No. of output : 2
No. of parameters : 32
100% (2000 of 2000) |####################| Elapsed Time: 0:51:02 ETA:  00:00:00

=== Performance result ===
Accuracy:  48.443671835917954 (+/-) 2.942444173339367
Precision:  0.5214009114521715
Recall:  0.48443671835917956
F1 score:  0.43294794070822784
Testing Time:  0.002092533913059435 (+/-) 0.0006810886525140304
Training Time:  1.5154523513148939 (+/-) 0.14269708464366124


=== Average network evolution ===
Total hidden node:  13.9965 (+/-) 13.9965


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=18, out_features=14, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 18
No. of nodes : 14
No. of parameters : 284

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=14, out_features=2, bias=True)
)
No. of inputs : 14
No. of output : 2
No. of parameters : 30
100% (2000 of 2000) |####################| Elapsed Time: 0:50:07 ETA:  00:00:00

=== Performance result ===
Accuracy:  54.79664832416208 (+/-) 1.7087315920626034
Precision:  0.6370388289627408
Recall:  0.5479664832416208
F1 score:  0.3987836492203695
Testing Time:  0.002073227375253789 (+/-) 0.0004930975134833653
Training Time:  1.488355452445461 (+/-) 0.037557004461820656


=== Average network evolution ===
Total hidden node:  14.994 (+/-) 14.994


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=18, out_features=15, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 18
No. of nodes : 15
No. of parameters : 303

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=15, out_features=2, bias=True)
)
No. of inputs : 15
No. of output : 2
No. of parameters : 32

========== Performance occupancy ==========
Preq Accuracy:  51.89 (+/-) 3.95
F1 score:  0.39 (+/-) 0.05
Precision:  0.57 (+/-) 0.06
Recall:  0.52 (+/-) 0.04
Training time:  1.43 (+/-) 0.06
Testing time:  0.0 (+/-) 0.0


========== Network ==========
Number of hidden layers:  1.0 (+/-) 0.0
Number of features:  11.2 (+/-) 4.31
In [ ]:
 
In [ ]:
 
In [12]:
%run DEVDAN_occupancy-ablation.ipynb
Number of input:  5
Number of output:  2
Number of batch:  20
Without Generative Phase
100% (20 of 20) |########################| Elapsed Time: 0:00:37 ETA:  00:00:00

=== Performance result ===
Accuracy:  93.57368421052632 (+/-) 12.156299735885836
Precision:  0.9354095930085677
Recall:  0.9357368421052632
F1 score:  0.9336798895720925
Testing Time:  0.0017215452696147718 (+/-) 0.00044726776982812177
Training Time:  1.955162148726614 (+/-) 0.029636624515251238


=== Average network evolution ===
Total hidden node:  30.05 (+/-) 13.063211703099663


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=5, out_features=47, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 5
No. of nodes : 47
No. of parameters : 287

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=47, out_features=2, bias=True)
)
No. of inputs : 47
No. of output : 2
No. of parameters : 96
100% (20 of 20) |########################| Elapsed Time: 0:00:39 ETA:  00:00:00

=== Performance result ===
Accuracy:  92.57368421052631 (+/-) 13.422951362077493
Precision:  0.9250918532028085
Recall:  0.9257368421052632
F1 score:  0.92299337444738
Testing Time:  0.0015000293129368832 (+/-) 0.0004957695660650428
Training Time:  2.0762069601761666 (+/-) 0.10863757866221659


=== Average network evolution ===
Total hidden node:  29.5 (+/-) 10.924742559895861


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=5, out_features=45, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 5
No. of nodes : 45
No. of parameters : 275

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=45, out_features=2, bias=True)
)
No. of inputs : 45
No. of output : 2
No. of parameters : 92
100% (20 of 20) |########################| Elapsed Time: 0:00:41 ETA:  00:00:00

=== Performance result ===
Accuracy:  93.1157894736842 (+/-) 12.79832485576036
Precision:  0.9320049652630612
Recall:  0.9311578947368421
F1 score:  0.9280837691227649
Testing Time:  0.0015570364500346937 (+/-) 0.000498296115491202
Training Time:  2.1909703831923637 (+/-) 0.14375092989333738


=== Average network evolution ===
Total hidden node:  34.5 (+/-) 10.781929326423912


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=5, out_features=49, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 5
No. of nodes : 49
No. of parameters : 299

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=49, out_features=2, bias=True)
)
No. of inputs : 49
No. of output : 2
No. of parameters : 100
100% (20 of 20) |########################| Elapsed Time: 0:00:38 ETA:  00:00:00

=== Performance result ===
Accuracy:  88.57368421052632 (+/-) 14.35621420941443
Precision:  0.8832427672236072
Recall:  0.8857368421052632
F1 score:  0.8782999480839504
Testing Time:  0.0016620912049946032 (+/-) 0.00046385915208133614
Training Time:  2.0400126733277975 (+/-) 0.10790820181123534


=== Average network evolution ===
Total hidden node:  23.8 (+/-) 11.311940593903417


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=5, out_features=40, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 5
No. of nodes : 40
No. of parameters : 245

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=40, out_features=2, bias=True)
)
No. of inputs : 40
No. of output : 2
No. of parameters : 82
100% (20 of 20) |########################| Elapsed Time: 0:00:37 ETA:  00:00:00

=== Performance result ===
Accuracy:  90.96842105263158 (+/-) 14.334428655350944
Precision:  0.9098439440373084
Recall:  0.9096842105263158
F1 score:  0.9045042669375507
Testing Time:  0.0015575634805779707 (+/-) 0.0005002158389697008
Training Time:  1.9723938264344867 (+/-) 0.04622126171582108


=== Average network evolution ===
Total hidden node:  26.0 (+/-) 13.435028842544403


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=5, out_features=44, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 5
No. of nodes : 44
No. of parameters : 269

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=44, out_features=2, bias=True)
)
No. of inputs : 44
No. of output : 2
No. of parameters : 90

========== Performance ==========
Preq Accuracy:  91.76 (+/-) 1.82
F1 score:  0.91 (+/-) 0.02
Precision:  0.92 (+/-) 0.02
Recall:  0.92 (+/-) 0.02
Training time:  2.05 (+/-) 0.08
Testing time:  0.0 (+/-) 0.0


========== Network ==========
Number of hidden layers:  1.0 (+/-) 0.0
Number of features:  45.0 (+/-) 3.03
Without Node Growing
100% (20 of 20) |########################| Elapsed Time: 0:00:51 ETA:  00:00:00

=== Performance result ===
Accuracy:  93.22105263157894 (+/-) 11.061387509205563
Precision:  0.9310473512530334
Recall:  0.9322105263157895
F1 score:  0.9307915888167794
Testing Time:  0.0012961563311125104 (+/-) 0.0004605102345438681
Training Time:  2.7318730103342155 (+/-) 0.09849592600050304


=== Average network evolution ===
Total hidden node:  2.0 (+/-) 0.0


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=5, out_features=2, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 5
No. of nodes : 2
No. of parameters : 17

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=2, out_features=2, bias=True)
)
No. of inputs : 2
No. of output : 2
No. of parameters : 6
100% (20 of 20) |########################| Elapsed Time: 0:00:56 ETA:  00:00:00

=== Performance result ===
Accuracy:  88.03157894736842 (+/-) 17.007554130648096
Precision:  0.8794058440952276
Recall:  0.8803157894736842
F1 score:  0.8703573223073371
Testing Time:  0.0013403516066701788 (+/-) 0.0004936956945676099
Training Time:  2.9934796534086527 (+/-) 0.27580916333792205


=== Average network evolution ===
Total hidden node:  2.0 (+/-) 0.0


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=5, out_features=2, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 5
No. of nodes : 2
No. of parameters : 17

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=2, out_features=2, bias=True)
)
No. of inputs : 2
No. of output : 2
No. of parameters : 6
100% (20 of 20) |########################| Elapsed Time: 0:00:55 ETA:  00:00:00

=== Performance result ===
Accuracy:  91.09473684210526 (+/-) 14.63648914201873
Precision:  0.9097408367071526
Recall:  0.9109473684210526
F1 score:  0.906880608026281
Testing Time:  0.001617883381090666 (+/-) 0.00048469349308078385
Training Time:  2.929529779835751 (+/-) 0.25433039202432345


=== Average network evolution ===
Total hidden node:  2.0 (+/-) 0.0


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=5, out_features=2, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 5
No. of nodes : 2
No. of parameters : 17

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=2, out_features=2, bias=True)
)
No. of inputs : 2
No. of output : 2
No. of parameters : 6
100% (20 of 20) |########################| Elapsed Time: 0:00:55 ETA:  00:00:00

=== Performance result ===
Accuracy:  91.16315789473686 (+/-) 13.571805547427154
Precision:  0.9115771379144545
Recall:  0.9116315789473685
F1 score:  0.9068440903674022
Testing Time:  0.0014144872364244964 (+/-) 0.0005900485199699953
Training Time:  2.9057316403639946 (+/-) 0.21580917278991182


=== Average network evolution ===
Total hidden node:  2.0 (+/-) 0.0


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=5, out_features=2, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 5
No. of nodes : 2
No. of parameters : 17

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=2, out_features=2, bias=True)
)
No. of inputs : 2
No. of output : 2
No. of parameters : 6
100% (20 of 20) |########################| Elapsed Time: 0:00:53 ETA:  00:00:00

=== Performance result ===
Accuracy:  66.1263157894737 (+/-) 30.02423305660145
Precision:  0.6182089531389595
Recall:  0.6612631578947369
F1 score:  0.6375445494182905
Testing Time:  0.00150827357643529 (+/-) 0.0004937362762175094
Training Time:  2.827217127147474 (+/-) 0.09335132160517298


=== Average network evolution ===
Total hidden node:  2.0 (+/-) 0.0


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=5, out_features=2, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 5
No. of nodes : 2
No. of parameters : 17

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=2, out_features=2, bias=True)
)
No. of inputs : 2
No. of output : 2
No. of parameters : 6

========== Performance ==========
Preq Accuracy:  85.93 (+/-) 10.04
F1 score:  0.85 (+/-) 0.11
Precision:  0.85 (+/-) 0.12
Recall:  0.86 (+/-) 0.1
Training time:  2.88 (+/-) 0.09
Testing time:  0.0 (+/-) 0.0


========== Network ==========
Number of hidden layers:  1.0 (+/-) 0.0
Number of features:  2.0 (+/-) 0.0
Without Node Pruning
100% (20 of 20) |########################| Elapsed Time: 0:00:54 ETA:  00:00:00

=== Performance result ===
Accuracy:  89.34736842105264 (+/-) 16.77110197619241
Precision:  0.8942125703570543
Recall:  0.8934736842105263
F1 score:  0.8853101906658994
Testing Time:  0.0016607485319438734 (+/-) 0.0004672761631468815
Training Time:  2.8557581148649516 (+/-) 0.18121124774363737


=== Average network evolution ===
Total hidden node:  41.45 (+/-) 15.419062876841771


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=5, out_features=60, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 5
No. of nodes : 60
No. of parameters : 365

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=60, out_features=2, bias=True)
)
No. of inputs : 60
No. of output : 2
No. of parameters : 122
100% (20 of 20) |########################| Elapsed Time: 0:00:53 ETA:  00:00:00

=== Performance result ===
Accuracy:  92.82631578947368 (+/-) 12.987842173407007
Precision:  0.9269162360829145
Recall:  0.9282631578947368
F1 score:  0.9267992093359675
Testing Time:  0.0020866268559506067 (+/-) 0.0005534460880592887
Training Time:  2.8215924689644263 (+/-) 0.10037888092560249


=== Average network evolution ===
Total hidden node:  49.8 (+/-) 10.514751542475931


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=5, out_features=63, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 5
No. of nodes : 63
No. of parameters : 383

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=63, out_features=2, bias=True)
)
No. of inputs : 63
No. of output : 2
No. of parameters : 128
100% (20 of 20) |########################| Elapsed Time: 0:00:52 ETA:  00:00:00

=== Performance result ===
Accuracy:  93.08947368421053 (+/-) 12.632243403576508
Precision:  0.9303692142927361
Recall:  0.9308947368421052
F1 score:  0.9285607545462513
Testing Time:  0.0018228857140792044 (+/-) 0.00036562200567119145
Training Time:  2.7697612988321403 (+/-) 0.17622557889511117


=== Average network evolution ===
Total hidden node:  39.35 (+/-) 14.468154685377124


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=5, out_features=58, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 5
No. of nodes : 58
No. of parameters : 353

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=58, out_features=2, bias=True)
)
No. of inputs : 58
No. of output : 2
No. of parameters : 118
100% (20 of 20) |########################| Elapsed Time: 0:00:51 ETA:  00:00:00

=== Performance result ===
Accuracy:  92.71052631578945 (+/-) 12.117837862417279
Precision:  0.9257116259072304
Recall:  0.9271052631578948
F1 score:  0.9257348938734065
Testing Time:  0.0017140790035850124 (+/-) 0.000444109980173383
Training Time:  2.7278683311060856 (+/-) 0.06939978773878293


=== Average network evolution ===
Total hidden node:  42.05 (+/-) 12.714067012565256


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=5, out_features=60, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 5
No. of nodes : 60
No. of parameters : 365

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=60, out_features=2, bias=True)
)
No. of inputs : 60
No. of output : 2
No. of parameters : 122
100% (20 of 20) |########################| Elapsed Time: 0:00:50 ETA:  00:00:00

=== Performance result ===
Accuracy:  92.97894736842105 (+/-) 12.37584995262392
Precision:  0.9291277423948574
Recall:  0.9297894736842105
F1 score:  0.9274584390969114
Testing Time:  0.001758675826223273 (+/-) 0.000411551638846052
Training Time:  2.6792213038394324 (+/-) 0.018530827724186166


=== Average network evolution ===
Total hidden node:  53.35 (+/-) 13.9329645086751


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=5, out_features=70, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 5
No. of nodes : 70
No. of parameters : 425

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=70, out_features=2, bias=True)
)
No. of inputs : 70
No. of output : 2
No. of parameters : 142

========== Performance ==========
Preq Accuracy:  92.19 (+/-) 1.43
F1 score:  0.92 (+/-) 0.02
Precision:  0.92 (+/-) 0.01
Recall:  0.92 (+/-) 0.01
Training time:  2.77 (+/-) 0.06
Testing time:  0.0 (+/-) 0.0


========== Network ==========
Number of hidden layers:  1.0 (+/-) 0.0
Number of features:  62.2 (+/-) 4.21
In [13]:
%run DEVDAN_creditcarddefault-ablation.ipynb
Number of input:  24
Number of output:  2
Number of batch:  30
Without Generative Phase
100% (30 of 30) |########################| Elapsed Time: 0:00:58 ETA:  00:00:00

=== Performance result ===
Accuracy:  80.75517241379309 (+/-) 2.4581442687799173
Precision:  0.7892019427565701
Recall:  0.8075517241379311
F1 score:  0.7686752798962437
Testing Time:  0.002075014443233095 (+/-) 0.00040529412902852056
Training Time:  2.014861509717744 (+/-) 0.042307318598226874


=== Average network evolution ===
Total hidden node:  9.833333333333334 (+/-) 0.37267799624996495


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=24, out_features=10, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 24
No. of nodes : 10
No. of parameters : 274

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=10, out_features=2, bias=True)
)
No. of inputs : 10
No. of output : 2
No. of parameters : 22
100% (30 of 30) |########################| Elapsed Time: 0:00:58 ETA:  00:00:00

=== Performance result ===
Accuracy:  80.56206896551727 (+/-) 2.2478209821196953
Precision:  0.785122533452928
Recall:  0.8056206896551724
F1 score:  0.7671577677581873
Testing Time:  0.002462082895739325 (+/-) 0.0005675301232885047
Training Time:  2.0267319761473557 (+/-) 0.05960429204693319


=== Average network evolution ===
Total hidden node:  10.966666666666667 (+/-) 0.9480975102218595


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=24, out_features=12, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 24
No. of nodes : 12
No. of parameters : 324

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=12, out_features=2, bias=True)
)
No. of inputs : 12
No. of output : 2
No. of parameters : 26
100% (30 of 30) |########################| Elapsed Time: 0:00:58 ETA:  00:00:00

=== Performance result ===
Accuracy:  80.82068965517243 (+/-) 2.267062402795488
Precision:  0.790507239445375
Recall:  0.8082068965517242
F1 score:  0.7693591866744017
Testing Time:  0.0021467455502214104 (+/-) 0.0003767043434993368
Training Time:  2.0179267011839768 (+/-) 0.05193487323095378


=== Average network evolution ===
Total hidden node:  13.2 (+/-) 0.5416025603090641


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=24, out_features=14, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 24
No. of nodes : 14
No. of parameters : 374

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=14, out_features=2, bias=True)
)
No. of inputs : 14
No. of output : 2
No. of parameters : 30
100% (30 of 30) |########################| Elapsed Time: 0:00:58 ETA:  00:00:00

=== Performance result ===
Accuracy:  80.4448275862069 (+/-) 2.172490420104516
Precision:  0.7836486405080502
Recall:  0.804448275862069
F1 score:  0.7644299192154417
Testing Time:  0.002009539768613618 (+/-) 0.00032250459829410766
Training Time:  2.017317089541205 (+/-) 0.01932895288136567


=== Average network evolution ===
Total hidden node:  13.233333333333333 (+/-) 0.8034647195462634


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=24, out_features=14, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 24
No. of nodes : 14
No. of parameters : 374

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=14, out_features=2, bias=True)
)
No. of inputs : 14
No. of output : 2
No. of parameters : 30
100% (30 of 30) |########################| Elapsed Time: 0:00:58 ETA:  00:00:00

=== Performance result ===
Accuracy:  80.64827586206897 (+/-) 2.3697258228799933
Precision:  0.7863984073661209
Recall:  0.8064827586206896
F1 score:  0.7687611865036567
Testing Time:  0.0022159280448124327 (+/-) 0.0005670748202569871
Training Time:  2.0239893485759866 (+/-) 0.04198224779478828


=== Average network evolution ===
Total hidden node:  10.2 (+/-) 0.7916228058025278


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=24, out_features=11, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 24
No. of nodes : 11
No. of parameters : 299

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=11, out_features=2, bias=True)
)
No. of inputs : 11
No. of output : 2
No. of parameters : 24

========== Performance ==========
Preq Accuracy:  80.65 (+/-) 0.13
F1 score:  0.77 (+/-) 0.0
Precision:  0.79 (+/-) 0.0
Recall:  0.81 (+/-) 0.0
Training time:  2.02 (+/-) 0.0
Testing time:  0.0 (+/-) 0.0


========== Network ==========
Number of hidden layers:  1.0 (+/-) 0.0
Number of features:  12.2 (+/-) 1.6
Without Node Growing
100% (30 of 30) |########################| Elapsed Time: 0:01:17 ETA:  00:00:00

=== Performance result ===
Accuracy:  80.21379310344827 (+/-) 2.4871704096923066
Precision:  0.7804464325282893
Recall:  0.8021379310344827
F1 score:  0.7593708743162471
Testing Time:  0.0020793964122903757 (+/-) 0.00047984794131673993
Training Time:  2.679647009948204 (+/-) 0.017859648861649674


=== Average network evolution ===
Total hidden node:  2.0 (+/-) 0.0


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=24, out_features=2, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 24
No. of nodes : 2
No. of parameters : 74

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=2, out_features=2, bias=True)
)
No. of inputs : 2
No. of output : 2
No. of parameters : 6
100% (30 of 30) |########################| Elapsed Time: 0:01:18 ETA:  00:00:00

=== Performance result ===
Accuracy:  80.14827586206896 (+/-) 2.4843816534023504
Precision:  0.780320280000189
Recall:  0.8014827586206896
F1 score:  0.7566657493213086
Testing Time:  0.0019522864243079875 (+/-) 0.00018179590242385895
Training Time:  2.714654642960121 (+/-) 0.05977906297909256


=== Average network evolution ===
Total hidden node:  2.0 (+/-) 0.0


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=24, out_features=2, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 24
No. of nodes : 2
No. of parameters : 74

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=2, out_features=2, bias=True)
)
No. of inputs : 2
No. of output : 2
No. of parameters : 6
100% (30 of 30) |########################| Elapsed Time: 0:01:21 ETA:  00:00:00C:\Users\SCSE\AppData\Local\Continuum\miniconda3\envs\stmicro\lib\site-packages\sklearn\metrics\_classification.py:1221: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))

=== Performance result ===
Accuracy:  77.85517241379311 (+/-) 2.505247762115322
Precision:  0.6061427871581452
Recall:  0.7785517241379311
F1 score:  0.6816138984678044
Testing Time:  0.0020787798125168374 (+/-) 0.0006611789320584703
Training Time:  2.804120581725548 (+/-) 0.21483715292091082


=== Average network evolution ===
Total hidden node:  2.0 (+/-) 0.0


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=24, out_features=2, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 24
No. of nodes : 2
No. of parameters : 74

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=2, out_features=2, bias=True)
)
No. of inputs : 2
No. of output : 2
No. of parameters : 6
100% (30 of 30) |########################| Elapsed Time: 0:01:21 ETA:  00:00:00

=== Performance result ===
Accuracy:  79.60344827586206 (+/-) 2.7007639734764064
Precision:  0.7752990342897405
Recall:  0.7960344827586207
F1 score:  0.7405883226407914
Testing Time:  0.0020143574681775324 (+/-) 0.0004109426995956416
Training Time:  2.798151813704392 (+/-) 0.14502516273757177


=== Average network evolution ===
Total hidden node:  2.0 (+/-) 0.0


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=24, out_features=2, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 24
No. of nodes : 2
No. of parameters : 74

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=2, out_features=2, bias=True)
)
No. of inputs : 2
No. of output : 2
No. of parameters : 6
100% (30 of 30) |########################| Elapsed Time: 0:01:18 ETA:  00:00:00

=== Performance result ===
Accuracy:  80.25172413793103 (+/-) 2.554727961717818
Precision:  0.781668875361991
Recall:  0.8025172413793104
F1 score:  0.7591090951895206
Testing Time:  0.0021172885237068966 (+/-) 0.0003446694873858148
Training Time:  2.7147968637532203 (+/-) 0.026166999146322756


=== Average network evolution ===
Total hidden node:  2.0 (+/-) 0.0


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=24, out_features=2, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 24
No. of nodes : 2
No. of parameters : 74

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=2, out_features=2, bias=True)
)
No. of inputs : 2
No. of output : 2
No. of parameters : 6

========== Performance ==========
Preq Accuracy:  79.61 (+/-) 0.91
F1 score:  0.74 (+/-) 0.03
Precision:  0.74 (+/-) 0.07
Recall:  0.8 (+/-) 0.01
Training time:  2.74 (+/-) 0.05
Testing time:  0.0 (+/-) 0.0


========== Network ==========
Number of hidden layers:  1.0 (+/-) 0.0
Number of features:  2.0 (+/-) 0.0
Without Node Pruning
100% (30 of 30) |########################| Elapsed Time: 0:01:19 ETA:  00:00:00

=== Performance result ===
Accuracy:  80.03793103448277 (+/-) 3.1093201156282793
Precision:  0.7744572583511895
Recall:  0.8003793103448276
F1 score:  0.7674301387864683
Testing Time:  0.002382878599495723 (+/-) 0.0004924165011141951
Training Time:  2.7337934395362593 (+/-) 0.026392461399504807


=== Average network evolution ===
Total hidden node:  40.733333333333334 (+/-) 5.21493581509452


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=24, out_features=42, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 24
No. of nodes : 42
No. of parameters : 1074

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=42, out_features=2, bias=True)
)
No. of inputs : 42
No. of output : 2
No. of parameters : 86
100% (30 of 30) |########################| Elapsed Time: 0:01:20 ETA:  00:00:00

=== Performance result ===
Accuracy:  79.88620689655173 (+/-) 4.175026255373238
Precision:  0.7720012833977559
Recall:  0.7988620689655173
F1 score:  0.7638115328660888
Testing Time:  0.0022832525187525257 (+/-) 0.0005328204348280083
Training Time:  2.767561542576757 (+/-) 0.08062269161081284


=== Average network evolution ===
Total hidden node:  27.0 (+/-) 1.632993161855452


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=24, out_features=28, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 24
No. of nodes : 28
No. of parameters : 724

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=28, out_features=2, bias=True)
)
No. of inputs : 28
No. of output : 2
No. of parameters : 58
100% (30 of 30) |########################| Elapsed Time: 0:01:19 ETA:  00:00:00

=== Performance result ===
Accuracy:  80.46206896551725 (+/-) 2.3958892659207156
Precision:  0.7834171683539525
Recall:  0.8046206896551724
F1 score:  0.765676998189201
Testing Time:  0.002281567146038187 (+/-) 0.0004673891362354464
Training Time:  2.7292368247591217 (+/-) 0.03493085020252392


=== Average network evolution ===
Total hidden node:  25.933333333333334 (+/-) 1.768866554856213


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=24, out_features=27, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 24
No. of nodes : 27
No. of parameters : 699

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=27, out_features=2, bias=True)
)
No. of inputs : 27
No. of output : 2
No. of parameters : 56
100% (30 of 30) |########################| Elapsed Time: 0:01:19 ETA:  00:00:00

=== Performance result ===
Accuracy:  80.73103448275862 (+/-) 2.357980352682891
Precision:  0.787572980234372
Recall:  0.8073103448275862
F1 score:  0.7703556553199438
Testing Time:  0.002456730809705011 (+/-) 0.0005025091839931565
Training Time:  2.7260219228678735 (+/-) 0.029212104585768846


=== Average network evolution ===
Total hidden node:  25.0 (+/-) 1.632993161855452


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=24, out_features=26, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 24
No. of nodes : 26
No. of parameters : 674

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=26, out_features=2, bias=True)
)
No. of inputs : 26
No. of output : 2
No. of parameters : 54
100% (30 of 30) |########################| Elapsed Time: 0:01:19 ETA:  00:00:00

=== Performance result ===
Accuracy:  80.38275862068966 (+/-) 2.5136961336010466
Precision:  0.7830245863448029
Recall:  0.8038275862068965
F1 score:  0.7626970037369322
Testing Time:  0.0024259008210280844 (+/-) 0.0004980262960594254
Training Time:  2.7389900602143387 (+/-) 0.050530964967255135


=== Average network evolution ===
Total hidden node:  38.733333333333334 (+/-) 5.597221532947296


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=24, out_features=40, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 24
No. of nodes : 40
No. of parameters : 1024

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=40, out_features=2, bias=True)
)
No. of inputs : 40
No. of output : 2
No. of parameters : 82

========== Performance ==========
Preq Accuracy:  80.3 (+/-) 0.3
F1 score:  0.77 (+/-) 0.0
Precision:  0.78 (+/-) 0.01
Recall:  0.8 (+/-) 0.0
Training time:  2.74 (+/-) 0.01
Testing time:  0.0 (+/-) 0.0


========== Network ==========
Number of hidden layers:  1.0 (+/-) 0.0
Number of features:  32.6 (+/-) 6.92
In [14]:
%run DEVDAN_rmnist-ablation.ipynb
Number of input:  784
Number of output:  10
Number of batch:  69
Without Generative Phase
100% (69 of 69) |########################| Elapsed Time: 0:02:38 ETA:  00:00:00

=== Performance result ===
Accuracy:  90.74558823529412 (+/-) 3.3949977832241487
Precision:  0.9074729874835634
Recall:  0.9074558823529412
F1 score:  0.9073866868023509
Testing Time:  0.016073510927312514 (+/-) 0.002530832043730629
Training Time:  2.318729702164145 (+/-) 0.05287749730356528


=== Average network evolution ===
Total hidden node:  28.318840579710145 (+/-) 3.2814487504944223


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=784, out_features=33, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 784
No. of nodes : 33
No. of parameters : 26689

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=33, out_features=10, bias=True)
)
No. of inputs : 33
No. of output : 10
No. of parameters : 340
100% (69 of 69) |########################| Elapsed Time: 0:02:37 ETA:  00:00:00

=== Performance result ===
Accuracy:  89.73823529411766 (+/-) 3.4354565332274984
Precision:  0.8973134271130122
Recall:  0.8973823529411765
F1 score:  0.8972720965098949
Testing Time:  0.015724255758173326 (+/-) 0.0020481363358425563
Training Time:  2.2998526446959553 (+/-) 0.048863628195707616


=== Average network evolution ===
Total hidden node:  24.202898550724637 (+/-) 1.1109430664774957


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=784, out_features=25, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 784
No. of nodes : 25
No. of parameters : 20409

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=25, out_features=10, bias=True)
)
No. of inputs : 25
No. of output : 10
No. of parameters : 260
100% (69 of 69) |########################| Elapsed Time: 0:02:38 ETA:  00:00:00

=== Performance result ===
Accuracy:  90.17794117647061 (+/-) 3.9301940375775835
Precision:  0.9020326225337904
Recall:  0.9017794117647059
F1 score:  0.9018472993806194
Testing Time:  0.015858702799853158 (+/-) 0.00249740114683838
Training Time:  2.3134974065948937 (+/-) 0.09613874162513862


=== Average network evolution ===
Total hidden node:  29.594202898550726 (+/-) 1.9950579562226385


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=784, out_features=32, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 784
No. of nodes : 32
No. of parameters : 25904

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=32, out_features=10, bias=True)
)
No. of inputs : 32
No. of output : 10
No. of parameters : 330
100% (69 of 69) |########################| Elapsed Time: 0:02:36 ETA:  00:00:00

=== Performance result ===
Accuracy:  89.70882352941176 (+/-) 3.85943211664304
Precision:  0.8969442578461202
Recall:  0.8970882352941176
F1 score:  0.8969661744703338
Testing Time:  0.015766459352829876 (+/-) 0.002882095631473873
Training Time:  2.2884698229677536 (+/-) 0.05335394177864605


=== Average network evolution ===
Total hidden node:  18.942028985507246 (+/-) 0.3762537677028163


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=784, out_features=19, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 784
No. of nodes : 19
No. of parameters : 15699

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=19, out_features=10, bias=True)
)
No. of inputs : 19
No. of output : 10
No. of parameters : 200
100% (69 of 69) |########################| Elapsed Time: 0:02:36 ETA:  00:00:00

=== Performance result ===
Accuracy:  89.67647058823529 (+/-) 3.7582895689966556
Precision:  0.896526854746833
Recall:  0.8967647058823529
F1 score:  0.8965610633230563
Testing Time:  0.01537406795165118 (+/-) 0.0028037546741805875
Training Time:  2.2901252963963676 (+/-) 0.0797856933058875


=== Average network evolution ===
Total hidden node:  20.855072463768117 (+/-) 0.6432562614832505


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=784, out_features=21, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 784
No. of nodes : 21
No. of parameters : 17269

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=21, out_features=10, bias=True)
)
No. of inputs : 21
No. of output : 10
No. of parameters : 220

========== Performance ==========
Preq Accuracy:  90.01 (+/-) 0.41
F1 score:  0.9 (+/-) 0.0
Precision:  0.9 (+/-) 0.0
Recall:  0.9 (+/-) 0.0
Training time:  2.3 (+/-) 0.01
Testing time:  0.02 (+/-) 0.0


========== Network ==========
Number of hidden layers:  1.0 (+/-) 0.0
Number of features:  26.0 (+/-) 5.66
Without Node Growing
100% (69 of 69) |########################| Elapsed Time: 0:03:24 ETA:  00:00:00

=== Performance result ===
Accuracy:  85.11911764705881 (+/-) 4.245421663840499
Precision:  0.8510873879611457
Recall:  0.8511911764705883
F1 score:  0.8508511516471564
Testing Time:  0.015504121780395508 (+/-) 0.0021028568446617053
Training Time:  2.985935453106375 (+/-) 0.035079603371983584


=== Average network evolution ===
Total hidden node:  10.0 (+/-) 0.0


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=784, out_features=10, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 784
No. of nodes : 10
No. of parameters : 8634

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=10, out_features=10, bias=True)
)
No. of inputs : 10
No. of output : 10
No. of parameters : 110
100% (69 of 69) |########################| Elapsed Time: 0:03:24 ETA:  00:00:00

=== Performance result ===
Accuracy:  86.83676470588233 (+/-) 3.6540028176912376
Precision:  0.868112661877498
Recall:  0.8683676470588235
F1 score:  0.8680880114344237
Testing Time:  0.015471297151902142 (+/-) 0.0022369018031844316
Training Time:  2.9970511934336495 (+/-) 0.04090249126190453


=== Average network evolution ===
Total hidden node:  10.0 (+/-) 0.0


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=784, out_features=10, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 784
No. of nodes : 10
No. of parameters : 8634

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=10, out_features=10, bias=True)
)
No. of inputs : 10
No. of output : 10
No. of parameters : 110
100% (69 of 69) |########################| Elapsed Time: 0:03:24 ETA:  00:00:00

=== Performance result ===
Accuracy:  86.65882352941175 (+/-) 3.5627251340263166
Precision:  0.8661992415208806
Recall:  0.8665882352941177
F1 score:  0.8662011724239246
Testing Time:  0.015501029351178338 (+/-) 0.002537465877940737
Training Time:  2.983953461927526 (+/-) 0.039112842625619024


=== Average network evolution ===
Total hidden node:  10.0 (+/-) 0.0


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=784, out_features=10, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 784
No. of nodes : 10
No. of parameters : 8634

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=10, out_features=10, bias=True)
)
No. of inputs : 10
No. of output : 10
No. of parameters : 110
100% (69 of 69) |########################| Elapsed Time: 0:03:23 ETA:  00:00:00

=== Performance result ===
Accuracy:  87.05588235294118 (+/-) 3.6740097646665353
Precision:  0.8700764624304511
Recall:  0.8705588235294117
F1 score:  0.8701850518274112
Testing Time:  0.01537177843206069 (+/-) 0.002733976772446847
Training Time:  2.980056222747354 (+/-) 0.026054172130583173


=== Average network evolution ===
Total hidden node:  10.0 (+/-) 0.0


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=784, out_features=10, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 784
No. of nodes : 10
No. of parameters : 8634

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=10, out_features=10, bias=True)
)
No. of inputs : 10
No. of output : 10
No. of parameters : 110
100% (69 of 69) |########################| Elapsed Time: 0:03:23 ETA:  00:00:00

=== Performance result ===
Accuracy:  86.95147058823531 (+/-) 3.8222449765680446
Precision:  0.8694087001872666
Recall:  0.8695147058823529
F1 score:  0.8690925095868817
Testing Time:  0.015403796644771801 (+/-) 0.002844179121641937
Training Time:  2.972826775382547 (+/-) 0.028841240482971073


=== Average network evolution ===
Total hidden node:  10.0 (+/-) 0.0


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=784, out_features=10, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 784
No. of nodes : 10
No. of parameters : 8634

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=10, out_features=10, bias=True)
)
No. of inputs : 10
No. of output : 10
No. of parameters : 110

========== Performance ==========
Preq Accuracy:  86.52 (+/-) 0.71
F1 score:  0.86 (+/-) 0.01
Precision:  0.86 (+/-) 0.01
Recall:  0.87 (+/-) 0.01
Training time:  2.98 (+/-) 0.01
Testing time:  0.02 (+/-) 0.0


========== Network ==========
Number of hidden layers:  1.0 (+/-) 0.0
Number of features:  10.0 (+/-) 0.0
Without Node Pruning
100% (69 of 69) |########################| Elapsed Time: 0:04:51 ETA:  00:00:00

=== Performance result ===
Accuracy:  90.94411764705883 (+/-) 4.56728720979395
Precision:  0.9094665761623717
Recall:  0.9094411764705882
F1 score:  0.9094234762693522
Testing Time:  0.01770170997170841 (+/-) 0.0029293736884793394
Training Time:  4.260714509907891 (+/-) 0.0853115246109465


=== Average network evolution ===
Total hidden node:  65.6376811594203 (+/-) 3.1206233792549014


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=784, out_features=68, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 784
No. of nodes : 68
No. of parameters : 54164

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=68, out_features=10, bias=True)
)
No. of inputs : 68
No. of output : 10
No. of parameters : 690
100% (69 of 69) |########################| Elapsed Time: 0:04:20 ETA:  00:00:00

=== Performance result ===
Accuracy:  89.63970588235291 (+/-) 3.6845520002988947
Precision:  0.896492834715607
Recall:  0.8963970588235294
F1 score:  0.8962698796242975
Testing Time:  0.017059203456429875 (+/-) 0.0031026038268762326
Training Time:  3.8178149742238663 (+/-) 0.4567385740052197


=== Average network evolution ===
Total hidden node:  38.26086956521739 (+/-) 8.997023942591598


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=784, out_features=44, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 784
No. of nodes : 44
No. of parameters : 35324

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=44, out_features=10, bias=True)
)
No. of inputs : 44
No. of output : 10
No. of parameters : 450
100% (69 of 69) |########################| Elapsed Time: 0:04:50 ETA:  00:00:00

=== Performance result ===
Accuracy:  91.00441176470588 (+/-) 4.4412317390406
Precision:  0.9102373840540025
Recall:  0.9100441176470588
F1 score:  0.9100179467337116
Testing Time:  0.016983239089741427 (+/-) 0.002016694740849741
Training Time:  4.245553668807535 (+/-) 0.0741036886837145


=== Average network evolution ===
Total hidden node:  66.89855072463769 (+/-) 1.252764219418801


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=784, out_features=70, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 784
No. of nodes : 70
No. of parameters : 55734

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=70, out_features=10, bias=True)
)
No. of inputs : 70
No. of output : 10
No. of parameters : 710
100% (69 of 69) |########################| Elapsed Time: 0:04:49 ETA:  00:00:00

=== Performance result ===
Accuracy:  91.63823529411764 (+/-) 3.9009059811854545
Precision:  0.9164836997315243
Recall:  0.9163823529411764
F1 score:  0.9163737730320589
Testing Time:  0.017834253170911002 (+/-) 0.002975104722708604
Training Time:  4.230127408223994 (+/-) 0.07497546593004517


=== Average network evolution ===
Total hidden node:  62.08695652173913 (+/-) 0.8118529608209226


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=784, out_features=64, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 784
No. of nodes : 64
No. of parameters : 51024

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=64, out_features=10, bias=True)
)
No. of inputs : 64
No. of output : 10
No. of parameters : 650
100% (69 of 69) |########################| Elapsed Time: 0:04:47 ETA:  00:00:00

=== Performance result ===
Accuracy:  91.88823529411764 (+/-) 3.9337352931280702
Precision:  0.9192029032083063
Recall:  0.9188823529411765
F1 score:  0.9189213501103894
Testing Time:  0.018216006896075082 (+/-) 0.004014107098851965
Training Time:  4.204413683975444 (+/-) 0.07302759036753052


=== Average network evolution ===
Total hidden node:  57.65217391304348 (+/-) 1.5306159313082242


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=784, out_features=58, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 784
No. of nodes : 58
No. of parameters : 46314

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=58, out_features=10, bias=True)
)
No. of inputs : 58
No. of output : 10
No. of parameters : 590

========== Performance ==========
Preq Accuracy:  91.02 (+/-) 0.78
F1 score:  0.91 (+/-) 0.01
Precision:  0.91 (+/-) 0.01
Recall:  0.91 (+/-) 0.01
Training time:  4.15 (+/-) 0.17
Testing time:  0.02 (+/-) 0.0


========== Network ==========
Number of hidden layers:  1.0 (+/-) 0.0
Number of features:  60.8 (+/-) 9.35
In [15]:
%run DEVDAN_sea-ablation.ipynb
Number of input:  3
Number of output:  2
Number of batch:  100
Without Generative Phase
100% (100 of 100) |######################| Elapsed Time: 0:03:21 ETA:  00:00:00

=== Performance result ===
Accuracy:  92.27878787878788 (+/-) 6.08869249581057
Precision:  0.9227983320267883
Recall:  0.9227878787878788
F1 score:  0.9222126425947392
Testing Time:  0.001395562682488952 (+/-) 0.0004930580679292113
Training Time:  2.028026397782143 (+/-) 0.026065904831567614


=== Average network evolution ===
Total hidden node:  22.48 (+/-) 11.036738648713214


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=3, out_features=41, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 3
No. of nodes : 41
No. of parameters : 167

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=41, out_features=2, bias=True)
)
No. of inputs : 41
No. of output : 2
No. of parameters : 84
100% (100 of 100) |######################| Elapsed Time: 0:03:20 ETA:  00:00:00

=== Performance result ===
Accuracy:  92.26060606060607 (+/-) 5.909704707825987
Precision:  0.9226098862598247
Recall:  0.9226060606060607
F1 score:  0.9220315998095829
Testing Time:  0.0014971843873611604 (+/-) 0.0005213897086913434
Training Time:  2.0237452454037137 (+/-) 0.03478457141079413


=== Average network evolution ===
Total hidden node:  24.03 (+/-) 10.923785973736393


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=3, out_features=43, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 3
No. of nodes : 43
No. of parameters : 175

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=43, out_features=2, bias=True)
)
No. of inputs : 43
No. of output : 2
No. of parameters : 88
100% (100 of 100) |######################| Elapsed Time: 0:03:20 ETA:  00:00:00

=== Performance result ===
Accuracy:  91.7181818181818 (+/-) 7.115417371523792
Precision:  0.9173894371460026
Recall:  0.9171818181818182
F1 score:  0.9164032247390432
Testing Time:  0.0013841860222093987 (+/-) 0.0004912996344615757
Training Time:  2.0270115823456734 (+/-) 0.03971917899283722


=== Average network evolution ===
Total hidden node:  15.64 (+/-) 8.498846980620371


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=3, out_features=30, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 3
No. of nodes : 30
No. of parameters : 123

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=30, out_features=2, bias=True)
)
No. of inputs : 30
No. of output : 2
No. of parameters : 62
100% (100 of 100) |######################| Elapsed Time: 0:03:21 ETA:  00:00:00

=== Performance result ===
Accuracy:  92.1222222222222 (+/-) 5.9849568246597675
Precision:  0.9209550208931403
Recall:  0.9212222222222223
F1 score:  0.920894743656429
Testing Time:  0.0014550974874785452 (+/-) 0.0004998964343142926
Training Time:  2.0351246053522285 (+/-) 0.043320118009483


=== Average network evolution ===
Total hidden node:  21.01 (+/-) 11.611627792863498


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=3, out_features=39, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 3
No. of nodes : 39
No. of parameters : 159

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=39, out_features=2, bias=True)
)
No. of inputs : 39
No. of output : 2
No. of parameters : 80
100% (100 of 100) |######################| Elapsed Time: 0:03:24 ETA:  00:00:00

=== Performance result ===
Accuracy:  91.82727272727273 (+/-) 6.739987983411315
Precision:  0.9180374596979158
Recall:  0.9182727272727272
F1 score:  0.9181062647800619
Testing Time:  0.0015477170847883128 (+/-) 0.0004973741247772138
Training Time:  2.064640310075548 (+/-) 0.09904460273522589


=== Average network evolution ===
Total hidden node:  22.32 (+/-) 14.969889779153352


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=3, out_features=47, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 3
No. of nodes : 47
No. of parameters : 191

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=47, out_features=2, bias=True)
)
No. of inputs : 47
No. of output : 2
No. of parameters : 96

========== Performance ==========
Preq Accuracy:  92.04 (+/-) 0.23
F1 score:  0.92 (+/-) 0.0
Precision:  0.92 (+/-) 0.0
Recall:  0.92 (+/-) 0.0
Training time:  2.04 (+/-) 0.01
Testing time:  0.0 (+/-) 0.0


========== Network ==========
Number of hidden layers:  1.0 (+/-) 0.0
Number of features:  40.0 (+/-) 5.66
Without Node Growing
100% (100 of 100) |######################| Elapsed Time: 0:04:26 ETA:  00:00:00

=== Performance result ===
Accuracy:  91.81313131313131 (+/-) 6.431419820066856
Precision:  0.9178442013534059
Recall:  0.9181313131313131
F1 score:  0.9177606499358827
Testing Time:  0.0014143929337010238 (+/-) 0.0004980447948747212
Training Time:  2.691780292626583 (+/-) 0.028998377744018197


=== Average network evolution ===
Total hidden node:  2.0 (+/-) 0.0


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=3, out_features=2, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 3
No. of nodes : 2
No. of parameters : 11

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=2, out_features=2, bias=True)
)
No. of inputs : 2
No. of output : 2
No. of parameters : 6
100% (100 of 100) |######################| Elapsed Time: 0:04:28 ETA:  00:00:00

=== Performance result ===
Accuracy:  62.74747474747475 (+/-) 7.867980673954783
Precision:  0.5661861988636364
Recall:  0.6274747474747475
F1 score:  0.508939710278005
Testing Time:  0.0014054582576559047 (+/-) 0.0005008244700854948
Training Time:  2.7096815277831725 (+/-) 0.05452799572566072


=== Average network evolution ===
Total hidden node:  2.0 (+/-) 0.0


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=3, out_features=2, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 3
No. of nodes : 2
No. of parameters : 11

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=2, out_features=2, bias=True)
)
No. of inputs : 2
No. of output : 2
No. of parameters : 6
100% (100 of 100) |######################| Elapsed Time: 0:04:29 ETA:  00:00:00

=== Performance result ===
Accuracy:  91.67171717171718 (+/-) 7.184200403326711
Precision:  0.9166007049466466
Recall:  0.9167171717171717
F1 score:  0.9161164302685715
Testing Time:  0.0013790130615234375 (+/-) 0.0004890834933230784
Training Time:  2.720866499525128 (+/-) 0.059100067244273406


=== Average network evolution ===
Total hidden node:  2.0 (+/-) 0.0


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=3, out_features=2, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 3
No. of nodes : 2
No. of parameters : 11

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=2, out_features=2, bias=True)
)
No. of inputs : 2
No. of output : 2
No. of parameters : 6
100% (100 of 100) |######################| Elapsed Time: 0:04:28 ETA:  00:00:00

=== Performance result ===
Accuracy:  91.49393939393939 (+/-) 6.891743239936887
Precision:  0.9146924653814028
Recall:  0.9149393939393939
F1 score:  0.9147686950269358
Testing Time:  0.0012775551189075816 (+/-) 0.0004573904328600576
Training Time:  2.710835081158262 (+/-) 0.03225102146056753


=== Average network evolution ===
Total hidden node:  2.0 (+/-) 0.0


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=3, out_features=2, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 3
No. of nodes : 2
No. of parameters : 11

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=2, out_features=2, bias=True)
)
No. of inputs : 2
No. of output : 2
No. of parameters : 6
100% (100 of 100) |######################| Elapsed Time: 0:04:27 ETA:  00:00:00

=== Performance result ===
Accuracy:  92.05454545454543 (+/-) 6.373893609316316
Precision:  0.9202795774102572
Recall:  0.9205454545454546
F1 score:  0.9203167576495773
Testing Time:  0.0013533794518673058 (+/-) 0.0004867193479383472
Training Time:  2.7031733845219468 (+/-) 0.03619830647806712


=== Average network evolution ===
Total hidden node:  2.0 (+/-) 0.0


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=3, out_features=2, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 3
No. of nodes : 2
No. of parameters : 11

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=2, out_features=2, bias=True)
)
No. of inputs : 2
No. of output : 2
No. of parameters : 6

========== Performance ==========
Preq Accuracy:  85.96 (+/-) 11.61
F1 score:  0.84 (+/-) 0.16
Precision:  0.85 (+/-) 0.14
Recall:  0.86 (+/-) 0.12
Training time:  2.71 (+/-) 0.01
Testing time:  0.0 (+/-) 0.0


========== Network ==========
Number of hidden layers:  1.0 (+/-) 0.0
Number of features:  2.0 (+/-) 0.0
Without Node Pruning
100% (100 of 100) |######################| Elapsed Time: 0:04:29 ETA:  00:00:00

=== Performance result ===
Accuracy:  92.26666666666667 (+/-) 5.848093879222701
Precision:  0.9224183782829053
Recall:  0.9226666666666666
F1 score:  0.9223276858285956
Testing Time:  0.0016037695335619378 (+/-) 0.000523361557737617
Training Time:  2.7228738707725446 (+/-) 0.05765343349300195


=== Average network evolution ===
Total hidden node:  30.36 (+/-) 13.565780478837183


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=3, out_features=52, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 3
No. of nodes : 52
No. of parameters : 211

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=52, out_features=2, bias=True)
)
No. of inputs : 52
No. of output : 2
No. of parameters : 106
100% (100 of 100) |######################| Elapsed Time: 0:04:27 ETA:  00:00:00

=== Performance result ===
Accuracy:  92.01919191919191 (+/-) 6.170763205546344
Precision:  0.920056916978132
Recall:  0.9201919191919192
F1 score:  0.9196699131790155
Testing Time:  0.0014270724672259707 (+/-) 0.0004975809934545357
Training Time:  2.699920324364094 (+/-) 0.040659852940174


=== Average network evolution ===
Total hidden node:  26.4 (+/-) 13.384319183283104


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=3, out_features=48, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 3
No. of nodes : 48
No. of parameters : 195

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=48, out_features=2, bias=True)
)
No. of inputs : 48
No. of output : 2
No. of parameters : 98
100% (100 of 100) |######################| Elapsed Time: 0:04:28 ETA:  00:00:00

=== Performance result ===
Accuracy:  92.0949494949495 (+/-) 6.306888549773765
Precision:  0.9206804588201766
Recall:  0.920949494949495
F1 score:  0.9206186199425602
Testing Time:  0.0015178280647354897 (+/-) 0.0004982504906615172
Training Time:  2.710491556109804 (+/-) 0.05266129989289533


=== Average network evolution ===
Total hidden node:  28.96 (+/-) 13.352093468816042


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=3, out_features=50, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 3
No. of nodes : 50
No. of parameters : 203

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=50, out_features=2, bias=True)
)
No. of inputs : 50
No. of output : 2
No. of parameters : 102
100% (100 of 100) |######################| Elapsed Time: 0:04:28 ETA:  00:00:00

=== Performance result ===
Accuracy:  91.93030303030302 (+/-) 6.070286208709386
Precision:  0.9194156050227037
Recall:  0.9193030303030303
F1 score:  0.9186110102668115
Testing Time:  0.0016246540377838443 (+/-) 0.00047985255511146164
Training Time:  2.704034027427134 (+/-) 0.03540775645141918


=== Average network evolution ===
Total hidden node:  29.66 (+/-) 9.55951881634217


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=3, out_features=45, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 3
No. of nodes : 45
No. of parameters : 183

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=45, out_features=2, bias=True)
)
No. of inputs : 45
No. of output : 2
No. of parameters : 92
100% (100 of 100) |######################| Elapsed Time: 0:04:27 ETA:  00:00:00

=== Performance result ===
Accuracy:  92.12121212121212 (+/-) 6.0422965853813935
Precision:  0.921024633425642
Recall:  0.9212121212121213
F1 score:  0.9207560055110752
Testing Time:  0.0014768056195191663 (+/-) 0.0005007150460000052
Training Time:  2.702960288885868 (+/-) 0.029190661705202983


=== Average network evolution ===
Total hidden node:  28.15 (+/-) 9.982359440533084


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=3, out_features=45, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 3
No. of nodes : 45
No. of parameters : 183

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=45, out_features=2, bias=True)
)
No. of inputs : 45
No. of output : 2
No. of parameters : 92

========== Performance ==========
Preq Accuracy:  92.09 (+/-) 0.11
F1 score:  0.92 (+/-) 0.0
Precision:  0.92 (+/-) 0.0
Recall:  0.92 (+/-) 0.0
Training time:  2.71 (+/-) 0.01
Testing time:  0.0 (+/-) 0.0


========== Network ==========
Number of hidden layers:  1.0 (+/-) 0.0
Number of features:  48.0 (+/-) 2.76
In [17]:
%run DEVDAN_weather-ablation.ipynb
Number of input:  8
Number of output:  2
Number of batch:  18
Without Generative Phase
100% (18 of 18) |########################| Elapsed Time: 0:00:34 ETA:  00:00:00

=== Performance result ===
Accuracy:  73.32352941176471 (+/-) 3.6269464407996237
Precision:  0.717146586666287
Recall:  0.7332352941176471
F1 score:  0.7154387322390723
Testing Time:  0.0018020938424503103 (+/-) 0.00037335248921221173
Training Time:  2.02371389725629 (+/-) 0.021460935868924527


=== Average network evolution ===
Total hidden node:  7.0 (+/-) 0.8819171036881969


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=10, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 10
No. of parameters : 98

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=10, out_features=2, bias=True)
)
No. of inputs : 10
No. of output : 2
No. of parameters : 22
100% (18 of 18) |########################| Elapsed Time: 0:00:34 ETA:  00:00:00

=== Performance result ===
Accuracy:  72.30000000000001 (+/-) 4.568691407445963
Precision:  0.7061116336041033
Recall:  0.723
F1 score:  0.70720626951906
Testing Time:  0.0017394879285027 (+/-) 0.00043316443577439675
Training Time:  2.033839506261489 (+/-) 0.04669395999362822


=== Average network evolution ===
Total hidden node:  10.555555555555555 (+/-) 1.0122703976826999


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=13, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 13
No. of parameters : 125

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=13, out_features=2, bias=True)
)
No. of inputs : 13
No. of output : 2
No. of parameters : 28
100% (18 of 18) |########################| Elapsed Time: 0:00:34 ETA:  00:00:00

=== Performance result ===
Accuracy:  73.12941176470588 (+/-) 4.088544211773464
Precision:  0.7324851113482681
Recall:  0.7312941176470589
F1 score:  0.7318705246657892
Testing Time:  0.0015668869018554688 (+/-) 0.0004894101802008571
Training Time:  2.0170879504259895 (+/-) 0.016408703337512886


=== Average network evolution ===
Total hidden node:  10.166666666666666 (+/-) 0.8333333333333334


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=12, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 12
No. of parameters : 116

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=12, out_features=2, bias=True)
)
No. of inputs : 12
No. of output : 2
No. of parameters : 26
100% (18 of 18) |########################| Elapsed Time: 0:00:34 ETA:  00:00:00

=== Performance result ===
Accuracy:  72.50588235294117 (+/-) 3.6658151470091216
Precision:  0.7185570805630662
Recall:  0.7250588235294118
F1 score:  0.7211381018695603
Testing Time:  0.001514448839075425 (+/-) 0.0004991862972807128
Training Time:  2.0181839325848747 (+/-) 0.015580035673095597


=== Average network evolution ===
Total hidden node:  7.555555555555555 (+/-) 0.7617394000445604


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=9, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 9
No. of parameters : 89

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=9, out_features=2, bias=True)
)
No. of inputs : 9
No. of output : 2
No. of parameters : 20
100% (18 of 18) |########################| Elapsed Time: 0:00:34 ETA:  00:00:00

=== Performance result ===
Accuracy:  74.7 (+/-) 3.1546417714032704
Precision:  0.7360842438750544
Recall:  0.747
F1 score:  0.7379007733762636
Testing Time:  0.0016206713283763213 (+/-) 0.00047401652175644394
Training Time:  2.0262389183044434 (+/-) 0.030630162510188352


=== Average network evolution ===
Total hidden node:  8.38888888888889 (+/-) 1.1613636089092707


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=11, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 11
No. of parameters : 107

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=11, out_features=2, bias=True)
)
No. of inputs : 11
No. of output : 2
No. of parameters : 24

========== Performance ==========
Preq Accuracy:  73.19 (+/-) 0.84
F1 score:  0.72 (+/-) 0.01
Precision:  0.72 (+/-) 0.01
Recall:  0.73 (+/-) 0.01
Training time:  2.02 (+/-) 0.01
Testing time:  0.0 (+/-) 0.0


========== Network ==========
Number of hidden layers:  1.0 (+/-) 0.0
Number of features:  11.0 (+/-) 1.41
Without Node Growing
100% (18 of 18) |########################| Elapsed Time: 0:00:46 ETA:  00:00:00C:\Users\SCSE\AppData\Local\Continuum\miniconda3\envs\stmicro\lib\site-packages\sklearn\metrics\_classification.py:1221: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))

=== Performance result ===
Accuracy:  68.60000000000001 (+/-) 4.105806505282918
Precision:  0.470596
Recall:  0.686
F1 score:  0.5582396204033215
Testing Time:  0.0011524032143985525 (+/-) 0.00038346635940878177
Training Time:  2.7305170367745792 (+/-) 0.05466876775781112


=== Average network evolution ===
Total hidden node:  2.0 (+/-) 0.0


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=2, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 2
No. of parameters : 26

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=2, out_features=2, bias=True)
)
No. of inputs : 2
No. of output : 2
No. of parameters : 6
100% (18 of 18) |########################| Elapsed Time: 0:00:46 ETA:  00:00:00

=== Performance result ===
Accuracy:  72.31176470588235 (+/-) 3.5308526470563613
Precision:  0.7052876317906593
Recall:  0.7231176470588235
F1 score:  0.705165319208252
Testing Time:  0.001453722224516027 (+/-) 0.0004898616459168563
Training Time:  2.7118058064404655 (+/-) 0.03708563594086276


=== Average network evolution ===
Total hidden node:  2.0 (+/-) 0.0


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=2, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 2
No. of parameters : 26

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=2, out_features=2, bias=True)
)
No. of inputs : 2
No. of output : 2
No. of parameters : 6
100% (18 of 18) |########################| Elapsed Time: 0:00:45 ETA:  00:00:00

=== Performance result ===
Accuracy:  72.49411764705883 (+/-) 3.7126921559675123
Precision:  0.7079655553845364
Recall:  0.7249411764705882
F1 score:  0.7083938635311748
Testing Time:  0.0016226488001206342 (+/-) 0.0004860521421664403
Training Time:  2.697818770128138 (+/-) 0.014741974455908125


=== Average network evolution ===
Total hidden node:  2.0 (+/-) 0.0


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=2, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 2
No. of parameters : 26

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=2, out_features=2, bias=True)
)
No. of inputs : 2
No. of output : 2
No. of parameters : 6
100% (18 of 18) |########################| Elapsed Time: 0:00:45 ETA:  00:00:00C:\Users\SCSE\AppData\Local\Continuum\miniconda3\envs\stmicro\lib\site-packages\sklearn\metrics\_classification.py:1221: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))

=== Performance result ===
Accuracy:  68.60000000000001 (+/-) 4.105806505282918
Precision:  0.470596
Recall:  0.686
F1 score:  0.5582396204033215
Testing Time:  0.00157468459185432 (+/-) 0.0004927724404940576
Training Time:  2.694782397326301 (+/-) 0.012845652896684082


=== Average network evolution ===
Total hidden node:  2.0 (+/-) 0.0


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=2, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 2
No. of parameters : 26

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=2, out_features=2, bias=True)
)
No. of inputs : 2
No. of output : 2
No. of parameters : 6
100% (18 of 18) |########################| Elapsed Time: 0:00:46 ETA:  00:00:00

=== Performance result ===
Accuracy:  74.19411764705882 (+/-) 3.090872823279629
Precision:  0.7288286982528666
Recall:  0.7419411764705882
F1 score:  0.7294950874873668
Testing Time:  0.001450945349300609 (+/-) 0.0004983682412269472
Training Time:  2.7258081436157227 (+/-) 0.06308574827617441


=== Average network evolution ===
Total hidden node:  2.0 (+/-) 0.0


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=2, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 2
No. of parameters : 26

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=2, out_features=2, bias=True)
)
No. of inputs : 2
No. of output : 2
No. of parameters : 6

========== Performance ==========
Preq Accuracy:  71.24 (+/-) 2.25
F1 score:  0.65 (+/-) 0.08
Precision:  0.62 (+/-) 0.12
Recall:  0.71 (+/-) 0.02
Training time:  2.71 (+/-) 0.01
Testing time:  0.0 (+/-) 0.0


========== Network ==========
Number of hidden layers:  1.0 (+/-) 0.0
Number of features:  2.0 (+/-) 0.0
Without Node Pruning
100% (18 of 18) |########################| Elapsed Time: 0:00:46 ETA:  00:00:00

=== Performance result ===
Accuracy:  74.85882352941178 (+/-) 3.664946644909663
Precision:  0.7409542655066169
Recall:  0.7485882352941177
F1 score:  0.7433799268800994
Testing Time:  0.001797044978422277 (+/-) 0.0005068418728250268
Training Time:  2.733143820482142 (+/-) 0.060492400574404546


=== Average network evolution ===
Total hidden node:  18.555555555555557 (+/-) 2.3856567281759875


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=21, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 21
No. of parameters : 197

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=21, out_features=2, bias=True)
)
No. of inputs : 21
No. of output : 2
No. of parameters : 44
100% (18 of 18) |########################| Elapsed Time: 0:00:46 ETA:  00:00:00

=== Performance result ===
Accuracy:  73.34705882352942 (+/-) 3.697871827871178
Precision:  0.7229257587608933
Recall:  0.7334705882352941
F1 score:  0.7257959466108125
Testing Time:  0.001614528543808881 (+/-) 0.0004771757342794189
Training Time:  2.7041431735543644 (+/-) 0.04836136542327823


=== Average network evolution ===
Total hidden node:  16.833333333333332 (+/-) 1.8027756377319946


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=20, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 20
No. of parameters : 188

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=20, out_features=2, bias=True)
)
No. of inputs : 20
No. of output : 2
No. of parameters : 42
100% (18 of 18) |########################| Elapsed Time: 0:00:45 ETA:  00:00:00

=== Performance result ===
Accuracy:  72.90588235294118 (+/-) 5.019194989149192
Precision:  0.7258622892084874
Recall:  0.7290588235294118
F1 score:  0.7273079509111081
Testing Time:  0.0013945803922765395 (+/-) 0.0004953211438070998
Training Time:  2.698570630129646 (+/-) 0.031339594367953194


=== Average network evolution ===
Total hidden node:  9.333333333333334 (+/-) 2.0


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=12, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 12
No. of parameters : 116

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=12, out_features=2, bias=True)
)
No. of inputs : 12
No. of output : 2
No. of parameters : 26
100% (18 of 18) |########################| Elapsed Time: 0:00:45 ETA:  00:00:00

=== Performance result ===
Accuracy:  74.2529411764706 (+/-) 2.7527777729282876
Precision:  0.7295687178580386
Recall:  0.7425294117647059
F1 score:  0.73028971472955
Testing Time:  0.0017963577719295725 (+/-) 0.0003798953793357341
Training Time:  2.6945171776939842 (+/-) 0.011669351608103885


=== Average network evolution ===
Total hidden node:  14.0 (+/-) 0.9428090415820634


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=16, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 16
No. of parameters : 152

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=16, out_features=2, bias=True)
)
No. of inputs : 16
No. of output : 2
No. of parameters : 34
100% (18 of 18) |########################| Elapsed Time: 0:00:46 ETA:  00:00:00

=== Performance result ===
Accuracy:  73.96470588235294 (+/-) 2.4996331910833223
Precision:  0.7265793328768682
Recall:  0.7396470588235294
F1 score:  0.7277933837706771
Testing Time:  0.0017454203437356388 (+/-) 0.0004240404233773277
Training Time:  2.707971418605131 (+/-) 0.04007195905055027


=== Average network evolution ===
Total hidden node:  13.166666666666666 (+/-) 2.034425935955617


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=16, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 16
No. of parameters : 152

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=16, out_features=2, bias=True)
)
No. of inputs : 16
No. of output : 2
No. of parameters : 34

========== Performance ==========
Preq Accuracy:  73.87 (+/-) 0.68
F1 score:  0.73 (+/-) 0.01
Precision:  0.73 (+/-) 0.01
Recall:  0.74 (+/-) 0.01
Training time:  2.71 (+/-) 0.01
Testing time:  0.0 (+/-) 0.0


========== Network ==========
Number of hidden layers:  1.0 (+/-) 0.0
Number of features:  17.0 (+/-) 3.22
In [18]:
%run DEVDAN_electricitypricing-ablation.ipynb
Number of input:  8
Number of output:  2
Number of batch:  45
Without Generative Phase
100% (45 of 45) |########################| Elapsed Time: 0:01:29 ETA:  00:00:00

=== Performance result ===
Accuracy:  68.16363636363636 (+/-) 6.779551168741687
Precision:  0.6796222056044412
Recall:  0.6816363636363636
F1 score:  0.6802467331972326
Testing Time:  0.0016081116416237571 (+/-) 0.00048428904177932403
Training Time:  2.032021262428977 (+/-) 0.037695231628309185


=== Average network evolution ===
Total hidden node:  11.555555555555555 (+/-) 1.9726525352153024


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=13, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 13
No. of parameters : 125

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=13, out_features=2, bias=True)
)
No. of inputs : 13
No. of output : 2
No. of parameters : 28
100% (45 of 45) |########################| Elapsed Time: 0:01:29 ETA:  00:00:00

=== Performance result ===
Accuracy:  68.55909090909091 (+/-) 7.071560139737013
Precision:  0.6830235440955863
Recall:  0.6855909090909091
F1 score:  0.6835298182858075
Testing Time:  0.0017789927395907316 (+/-) 0.00045360356112352434
Training Time:  2.0232455188577827 (+/-) 0.022242758710080825


=== Average network evolution ===
Total hidden node:  5.866666666666666 (+/-) 0.8055363982396381


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=7, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 7
No. of parameters : 71

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=7, out_features=2, bias=True)
)
No. of inputs : 7
No. of output : 2
No. of parameters : 16
100% (45 of 45) |########################| Elapsed Time: 0:01:29 ETA:  00:00:00

=== Performance result ===
Accuracy:  68.08409090909089 (+/-) 7.255591673818896
Precision:  0.677266842340992
Recall:  0.6808409090909091
F1 score:  0.6767609054950063
Testing Time:  0.001635101708498868 (+/-) 0.00047824708938723964
Training Time:  2.0259444551034407 (+/-) 0.03580335731647419


=== Average network evolution ===
Total hidden node:  11.977777777777778 (+/-) 1.2380789579719216


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=13, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 13
No. of parameters : 125

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=13, out_features=2, bias=True)
)
No. of inputs : 13
No. of output : 2
No. of parameters : 28
100% (45 of 45) |########################| Elapsed Time: 0:01:28 ETA:  00:00:00

=== Performance result ===
Accuracy:  68.48409090909091 (+/-) 7.7779683951126914
Precision:  0.6812923476078304
Recall:  0.6848409090909091
F1 score:  0.6796748413792804
Testing Time:  0.0016808455640619452 (+/-) 0.0004581021234020211
Training Time:  2.0156031413511797 (+/-) 0.021503036256615385


=== Average network evolution ===
Total hidden node:  9.244444444444444 (+/-) 1.0144633076011846


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=10, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 10
No. of parameters : 98

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=10, out_features=2, bias=True)
)
No. of inputs : 10
No. of output : 2
No. of parameters : 22
100% (45 of 45) |########################| Elapsed Time: 0:01:29 ETA:  00:00:00

=== Performance result ===
Accuracy:  67.92272727272729 (+/-) 6.4734374610390315
Precision:  0.6754409192883752
Recall:  0.6792272727272727
F1 score:  0.6730382504720993
Testing Time:  0.0014806281436573374 (+/-) 0.0005044863602579456
Training Time:  2.0257754000750454 (+/-) 0.03340499801956638


=== Average network evolution ===
Total hidden node:  8.155555555555555 (+/-) 2.0865234834320887


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=10, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 10
No. of parameters : 98

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=10, out_features=2, bias=True)
)
No. of inputs : 10
No. of output : 2
No. of parameters : 22

========== Performance ==========
Preq Accuracy:  68.24 (+/-) 0.24
F1 score:  0.68 (+/-) 0.0
Precision:  0.68 (+/-) 0.0
Recall:  0.68 (+/-) 0.0
Training time:  2.02 (+/-) 0.01
Testing time:  0.0 (+/-) 0.0


========== Network ==========
Number of hidden layers:  1.0 (+/-) 0.0
Number of features:  10.6 (+/-) 2.24
Without Node Growing
100% (45 of 45) |########################| Elapsed Time: 0:02:01 ETA:  00:00:00

=== Performance result ===
Accuracy:  68.4659090909091 (+/-) 6.573360258090577
Precision:  0.6818972331440835
Recall:  0.6846590909090909
F1 score:  0.6823283726238462
Testing Time:  0.0015494660897688432 (+/-) 0.0004913935251121107
Training Time:  2.753814561800523 (+/-) 0.11748496481473741


=== Average network evolution ===
Total hidden node:  2.0 (+/-) 0.0


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=2, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 2
No. of parameters : 26

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=2, out_features=2, bias=True)
)
No. of inputs : 2
No. of output : 2
No. of parameters : 6
100% (45 of 45) |########################| Elapsed Time: 0:01:58 ETA:  00:00:00

=== Performance result ===
Accuracy:  67.61363636363637 (+/-) 5.517887890928875
Precision:  0.6754462559804574
Recall:  0.6761363636363636
F1 score:  0.6619221116730928
Testing Time:  0.0014404491944746537 (+/-) 0.0005070220445672582
Training Time:  2.6986123485998674 (+/-) 0.028780528145456872


=== Average network evolution ===
Total hidden node:  2.0 (+/-) 0.0


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=2, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 2
No. of parameters : 26

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=2, out_features=2, bias=True)
)
No. of inputs : 2
No. of output : 2
No. of parameters : 6
100% (45 of 45) |########################| Elapsed Time: 0:02:00 ETA:  00:00:00

=== Performance result ===
Accuracy:  66.54318181818181 (+/-) 6.346237171715964
Precision:  0.6609678450088046
Recall:  0.6654318181818182
F1 score:  0.6570960355615786
Testing Time:  0.0015094659545204856 (+/-) 0.0005003074585927562
Training Time:  2.726659216664054 (+/-) 0.04762583667130423


=== Average network evolution ===
Total hidden node:  2.0 (+/-) 0.0


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=2, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 2
No. of parameters : 26

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=2, out_features=2, bias=True)
)
No. of inputs : 2
No. of output : 2
No. of parameters : 6
100% (45 of 45) |########################| Elapsed Time: 0:01:59 ETA:  00:00:00

=== Performance result ===
Accuracy:  59.83636363636364 (+/-) 6.767942177819935
Precision:  0.5886892969051388
Recall:  0.5983636363636363
F1 score:  0.5876577890245466
Testing Time:  0.0014139901507984507 (+/-) 0.0004965873925558917
Training Time:  2.7038654685020447 (+/-) 0.03197107613745281


=== Average network evolution ===
Total hidden node:  2.0 (+/-) 0.0


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=2, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 2
No. of parameters : 26

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=2, out_features=2, bias=True)
)
No. of inputs : 2
No. of output : 2
No. of parameters : 6
100% (45 of 45) |########################| Elapsed Time: 0:01:59 ETA:  00:00:00

=== Performance result ===
Accuracy:  65.86590909090908 (+/-) 7.413070250388167
Precision:  0.6549165834345053
Recall:  0.6586590909090909
F1 score:  0.6554079500954676
Testing Time:  0.001485830003565008 (+/-) 0.0005010854025706715
Training Time:  2.7098382169550117 (+/-) 0.036503107550605186


=== Average network evolution ===
Total hidden node:  2.0 (+/-) 0.0


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=2, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 2
No. of parameters : 26

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=2, out_features=2, bias=True)
)
No. of inputs : 2
No. of output : 2
No. of parameters : 6

========== Performance ==========
Preq Accuracy:  65.67 (+/-) 3.05
F1 score:  0.65 (+/-) 0.03
Precision:  0.65 (+/-) 0.03
Recall:  0.66 (+/-) 0.03
Training time:  2.72 (+/-) 0.02
Testing time:  0.0 (+/-) 0.0


========== Network ==========
Number of hidden layers:  1.0 (+/-) 0.0
Number of features:  2.0 (+/-) 0.0
Without Node Pruning
100% (45 of 45) |########################| Elapsed Time: 0:01:59 ETA:  00:00:00

=== Performance result ===
Accuracy:  67.6340909090909 (+/-) 7.703686932590908
Precision:  0.6729065601128338
Recall:  0.676340909090909
F1 score:  0.6730172902716484
Testing Time:  0.0017032189802689986 (+/-) 0.0004479726902760726
Training Time:  2.7149289629676123 (+/-) 0.03997734755367686


=== Average network evolution ===
Total hidden node:  17.466666666666665 (+/-) 2.49087222563592


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=20, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 20
No. of parameters : 188

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=20, out_features=2, bias=True)
)
No. of inputs : 20
No. of output : 2
No. of parameters : 42
100% (45 of 45) |########################| Elapsed Time: 0:01:58 ETA:  00:00:00

=== Performance result ===
Accuracy:  67.27499999999999 (+/-) 7.092701914964808
Precision:  0.6687702446639067
Recall:  0.67275
F1 score:  0.6680440931347955
Testing Time:  0.0017780769955028188 (+/-) 0.0004032561564487275
Training Time:  2.6993932832371104 (+/-) 0.02849194179461089


=== Average network evolution ===
Total hidden node:  11.71111111111111 (+/-) 1.6278441397166612


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=13, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 13
No. of parameters : 125

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=13, out_features=2, bias=True)
)
No. of inputs : 13
No. of output : 2
No. of parameters : 28
100% (45 of 45) |########################| Elapsed Time: 0:01:59 ETA:  00:00:00

=== Performance result ===
Accuracy:  69.30909090909091 (+/-) 7.0455923740184145
Precision:  0.6904108642859478
Recall:  0.6930909090909091
F1 score:  0.690698709534611
Testing Time:  0.002131386236710982 (+/-) 0.0024418435481554056
Training Time:  2.7083996805277737 (+/-) 0.03501783156360387


=== Average network evolution ===
Total hidden node:  22.08888888888889 (+/-) 2.8969119360850613


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=25, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 25
No. of parameters : 233

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=25, out_features=2, bias=True)
)
No. of inputs : 25
No. of output : 2
No. of parameters : 52
100% (45 of 45) |########################| Elapsed Time: 0:01:59 ETA:  00:00:00

=== Performance result ===
Accuracy:  68.67045454545456 (+/-) 6.91613987007777
Precision:  0.6834212766380879
Recall:  0.6867045454545454
F1 score:  0.6831148238189384
Testing Time:  0.0015842210162769663 (+/-) 0.0004870221919743115
Training Time:  2.7041912620717827 (+/-) 0.02951922653926562


=== Average network evolution ===
Total hidden node:  17.22222222222222 (+/-) 1.8121673811444547


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=19, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 19
No. of parameters : 179

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=19, out_features=2, bias=True)
)
No. of inputs : 19
No. of output : 2
No. of parameters : 40
100% (45 of 45) |########################| Elapsed Time: 0:01:59 ETA:  00:00:00

=== Performance result ===
Accuracy:  68.22954545454544 (+/-) 6.998135451203301
Precision:  0.6795280633449224
Recall:  0.6822954545454546
F1 score:  0.6800028141616109
Testing Time:  0.0015651095997203481 (+/-) 0.0004924211515183373
Training Time:  2.7061337449333887 (+/-) 0.039544123731576994


=== Average network evolution ===
Total hidden node:  14.71111111111111 (+/-) 2.0069016719778907


=== Final network structure ===

 1 -th layer
hiddenLayerBasicNet(
  (linear): Linear(in_features=8, out_features=16, bias=True)
  (activation): Sigmoid()
  (activationh): ReLU(inplace=True)
)
No. of inputs : 8
No. of nodes : 16
No. of parameters : 152

 2 -th layer
outputLayerBasicNet(
  (linearOutput): Linear(in_features=16, out_features=2, bias=True)
)
No. of inputs : 16
No. of output : 2
No. of parameters : 34

========== Performance ==========
Preq Accuracy:  68.22 (+/-) 0.72
F1 score:  0.68 (+/-) 0.01
Precision:  0.68 (+/-) 0.01
Recall:  0.68 (+/-) 0.01
Training time:  2.71 (+/-) 0.01
Testing time:  0.0 (+/-) 0.0


========== Network ==========
Number of hidden layers:  1.0 (+/-) 0.0
Number of features:  18.6 (+/-) 4.03
In [ ]:
 
In [ ]: